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

    Neuronpedia

    INDEX
    Explanations

    multiple topics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     llen
    -0.07
    lista
    -0.06
    &amp
    -0.06
     Riot
    -0.06
     Courtesy
    -0.06
    誰
    -0.06
     تع
    -0.06
    �
    -0.06
     FLOAT
    -0.06
    -done
    -0.06
    POSITIVE LOGITS
    -dem
    0.07
     "[
    0.06
    uary
    0.06
    .js
    0.06
    -im
    0.06
    マ
    0.06
     dramatically
    0.06
    inous
    0.06
    _cc
    0.06
    datas
    0.06
    Act Density 0.000%

    No Known Activations