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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /=
    -0.07
    ený
    -0.07
    نتی
    -0.07
    گذ
    -0.06
    ++)
    -0.06
     /.
    -0.06
    (dat
    -0.06
    ederation
    -0.06
    -pencil
    -0.06
     अगस
    -0.06
    POSITIVE LOGITS
    技术
    0.06
    BERT
    0.06
    ちょ
    0.06
     charged
    0.06
     trest
    0.06
     incentiv
    0.06
    .cap
    0.06
    业
    0.06
     inland
    0.06
    _valor
    0.06
    Act Density 0.070%

    No Known Activations