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

    Neuronpedia

    INDEX
    Explanations

    star

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Accuracy
    -0.07
     memories
    -0.07
    鸟
    -0.07
     Welfare
    -0.07
    _extractor
    -0.07
    cepts
    -0.07
    ателя
    -0.06
    avn
    -0.06
    同步
    -0.06
     DAYS
    -0.06
    POSITIVE LOGITS
     governed
    0.07
    .gold
    0.06
     unfamiliar
    0.06
    bff
    0.06
     vas
    0.06
    (holder
    0.06
     Шев
    0.06
    tingham
    0.06
    __(*
    0.06
    eresa
    0.06
    Act Density 0.017%

    No Known Activations