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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Clown
    -0.07
     são
    -0.07
     fuera
    -0.07
     जनवर
    -0.07
     станет
    -0.06
     mezi
    -0.06
     ano
    -0.06
     Đo
    -0.06
     досяг
    -0.06
     prer
    -0.06
    POSITIVE LOGITS
    _unpack
    0.07
     Bundesliga
    0.06
    Collapsed
    0.06
    ToObject
    0.06
     dorsal
    0.06
    ENAME
    0.06
    _CONN
    0.06
     patrons
    0.06
    .same
    0.06
    olvency
    0.06
    Act Density 0.000%

    No Known Activations