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

    Neuronpedia

    INDEX
    Explanations

    statements about societal issues, particularly those involving justice and truth

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

    Tokens before a colon or dash

    np_acts-logits-general · gemini-2.0-flash

    truth or conclusion followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    InitVars
    -0.89
     وتسجيلات
    -0.83
    OGND
    -0.82
    NameInMap
    -0.76
    AddTagHelper
    -0.72
    DockStyle
    -0.72
    Fns
    -0.67
    IUrlHelper
    -0.67
     jspb
    -0.67
     typelib
    -0.66
    POSITIVE LOGITS
    :
    1.20
    ：
    0.82
    __:
    0.80
    %:
    0.76
     :
    0.74
    ():
    0.73
    :
    0.68
    ~:
    0.67
     _:
    0.67
    _:
    0.66
    Act Density 0.401%

    No Known Activations