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

    Neuronpedia

    INDEX
    Explanations

    conditional statements with words like "if", "you", "would", etc

    oai_token-act-pair · gemini-2.0-flash

    phrases indicating inquiries or conditions

    np_token-act-pair-logits · gpt-4o-mini

    if

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Englishman
    -0.43
    |}{$
    -0.43
     acceptance
    -0.43
     Englishmen
    -0.43
    ueba
    -0.42
     exercí
    -0.42
     [],
    -0.41
    Facades
    -0.40
    Com
    -0.39
     molta
    -0.39
    POSITIVE LOGITS
    contentLoaded
    1.08
    Its
    1.07
     Its
    1.03
     its
    1.01
     Thats
    0.92
    Thats
    0.91
     shes
    0.89
     thats
    0.86
    tagHelperRunner
    0.85
    TypedDataSet
    0.81
    Act Density 0.654%

    No Known Activations