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

    Neuronpedia

    INDEX
    Explanations

    code syntax

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    举报电话
    -0.08
    -disabled
    -0.07
    邓小
    -0.07
    _produk
    -0.07
    _hidden
    -0.06
    ように
    -0.06
    쥔
    -0.06
     contador
    -0.06
    ptom
    -0.06
     Partnership
    -0.06
    POSITIVE LOGITS
    .Fat
    0.08
     winding
    0.07
    .fields
    0.07
    *self
    0.07
     VIII
    0.07
    水泥
    0.07
    ereal
    0.07
     AVG
    0.07
    .getCell
    0.07
     private
    0.07
    Act Density 0.167%

    No Known Activations