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

    Neuronpedia

    INDEX
    Explanations

    People and villages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sixth
    -0.06
     Though
    -0.06
     livre
    -0.06
     purity
    -0.06
     ves
    -0.06
     Stad
    -0.06
    .valid
    -0.06
    封
    -0.06
     Come
    -0.06
    ToShow
    -0.06
    POSITIVE LOGITS
     gangbang
    0.06
    ระบบ
    0.06
    09
    0.06
    cause
    0.06
    zelf
    0.06
    icious
    0.06
    [...,
    0.06
    _InitStructure
    0.06
    ۀ
    0.06
    ulus
    0.06
    Act Density 0.039%

    No Known Activations