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

    Neuronpedia

    INDEX
    Explanations

    significant numeric indicators or specific formatting in programming contexts

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

    Text following numbers or a period

    np_acts-logits-general · gemini-2.0-flash

    future studies caused opinion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    inner
    -0.55
     (
    -0.51
    std
    -0.48
     Ground
    -0.47
     E
    -0.45
     Au
    -0.45
    med
    -0.45
     inner
    -0.44
    ced
    -0.44
    rins
    -0.43
    POSITIVE LOGITS
    ArgsConstructor
    0.91
    TintMode
    0.89
     Мексичка
    0.89
    NUMX
    0.88
    extAlignment
    0.83
    AddHtmlAttribute
    0.81
     المعيارى
    0.80
    IsMutable
    0.80
     kaarangay
    0.79
    Portale
    0.78
    Act Density 0.042%

    No Known Activations