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

    Neuronpedia

    INDEX
    Explanations

    the presence of specific numerical or coding patterns in data

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

    Appears before uncommon characters or symbols

    np_acts-logits-general · gemini-2.0-flash

    new followed by a noun, number, or symbol

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    UnusedPrivate
    -0.50
    glClear
    -0.48
    cshtml
    -0.48
     censi
    -0.46
     everything
    -0.45
    .
    -0.44
     certain
    -0.44
     plans
    -0.43
     came
    -0.42
    end
    -0.42
    POSITIVE LOGITS
     متعلقه
    0.88
    AddTagHelper
    0.85
    ethene
    0.74
    extAlignment
    0.68
    CloseOperation
    0.66
    Filmografie
    0.64
    thâu
    0.64
     Roskov
    0.64
    lamabad
    0.63
    enumi
    0.63
    Act Density 0.730%

    No Known Activations