Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to political figures and their actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows "Trump", "Putin", or abbreviations

    np_acts-logits-general · gemini-2.0-flash

    ordered, ordering, blamed, used

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     समीक्षाएं
    -0.50
    ConstraintMaker
    -0.48
    contentLoaded
    -0.47
     reproducir
    -0.46
     cooperativa
    -0.45
    portada
    -0.45
    inja
    -0.45
     sections
    -0.43
     section
    -0.43
     sezione
    -0.43
    POSITIVE LOGITS
     personally
    1.15
     ordering
    1.14
     ordered
    1.12
     persönlich
    0.96
    ordered
    0.94
     orders
    0.93
     order
    0.91
     personalmente
    0.91
     Ordered
    0.90
    ordering
    0.88
    Act Density 0.370%

    No Known Activations