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

    Neuronpedia

    INDEX
    Explanations

    intervention

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ätz
    -0.07
     Instagram
    -0.07
     imdb
    -0.06
     Lawyers
    -0.06
    _nullable
    -0.06
     =================================================================
    -0.06
    ิก
    -0.06
     zv
    -0.06
     weekday
    -0.06
    ка
    -0.06
    POSITIVE LOGITS
    년에는
    0.07
    idot
    0.07
     Intervention
    0.06
    ritel
    0.06
    】,
    0.06
    larını
    0.06
     denně
    0.06
    So
    0.06
    -muted
    0.06
    "urls
    0.06
    Act Density 0.014%

    No Known Activations