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

    Neuronpedia

    INDEX
    Explanations

    government and finance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    aaaa
    -0.07
    AI
    -0.07
     urlencode
    -0.07
     Поль
    -0.06
    andan
    -0.06
     τελευτα
    -0.06
     will
    -0.06
     Accountability
    -0.06
    83
    -0.06
     Tent
    -0.06
    POSITIVE LOGITS
     saya
    0.07
    _ver
    0.06
    AGES
    0.06
    _dot
    0.06
    Double
    0.06
    ighet
    0.06
     Lap
    0.06
     Сим
    0.06
     Hitler
    0.06
    /password
    0.06
    Act Density 0.001%

    No Known Activations