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

    Neuronpedia

    INDEX
    Explanations

    country

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    icha
    -0.07
     Tut
    -0.07
    _Final
    -0.07
    chool
    -0.07
    udence
    -0.06
    ickers
    -0.06
     Loves
    -0.06
    елів
    -0.06
     fires
    -0.06
     pooling
    -0.06
    POSITIVE LOGITS
     don
    0.07
     LIMITED
    0.06
     pepp
    0.06
     getInfo
    0.06
     J
    0.06
     Vice
    0.06
     ■
    0.06
    Body
    0.06
     долж
    0.06
     atm
    0.06
    Act Density 0.038%

    No Known Activations