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

    Neuronpedia

    INDEX
    Explanations

    situations involving teaching, proving, or disagreeing

    oai_token-act-pair · gemini-2.0-flash

    academic/legal writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.84
     propOrder
    -0.82
     мәкал
    -0.81
     resourceCulture
    -0.81
    الحياه
    -0.79
    ConstraintMaker
    -0.79
    -0.78
     ویکی‌پدی
    -0.77
    Ligações
    -0.76
     odkazy
    -0.76
    POSITIVE LOGITS
     друг
    0.44
    elum
    0.41
    izas
    0.40
    γχ
    0.40
    äs
    0.40
    zwischen
    0.39
    kur
    0.39
    IFY
    0.39
    toHaveBeenCalled
    0.39
    ại
    0.38
    Act Density 0.618%

    No Known Activations