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

    Neuronpedia

    INDEX
    Explanations

    names of individuals and titles

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

    Code snippets or mathematical formulas

    np_acts-logits-general · gemini-2.0-flash

    proper nouns and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     the
    -0.59
    5
    -0.58
    4
    -0.58
     a
    -0.57
    3
    -0.56
    1
    -0.56
    2
    -0.56
     
    -0.55
    6
    -0.54
    뀐
    -0.53
    POSITIVE LOGITS
    Portale
    0.94
     ویکی‌پدیا
    0.93
     sánchez
    0.91
     démocr
    0.90
     enfans
    0.87
     rodríguez
    0.86
     fernández
    0.84
    UIControlState
    0.84
     houſe
    0.82
     lópez
    0.82
    Act Density 0.638%

    No Known Activations