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

    Neuronpedia

    INDEX
    Explanations

    words related to government agencies, laws, and funding

    oai_token-act-pair · gemini-2.0-flash

    agency

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     agency
    -0.87
     Agencies
    -0.84
     Agency
    -0.84
     AGENCY
    -0.79
     agencies
    -0.78
    agency
    -0.77
    Agency
    -0.77
     expensive
    -0.75
    agencies
    -0.73
    Agencies
    -0.71
    POSITIVE LOGITS
    parsedMessage
    0.89
    ագրություններ
    0.68
    ArgsConstructor
    0.64
     وتسجيلات
    0.62
     Colón
    0.60
    ineno
    0.60
     nahilalakip
    0.59
    Архівовано
    0.59
     Chwiliwch
    0.58
    PSO
    0.56
    Act Density 14.653%

    No Known Activations