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

    Neuronpedia

    INDEX
    Explanations

    HTML

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sonuç
    -0.06
    итом
    -0.06
     ві
    -0.06
     Subway
    -0.06
     Abraham
    -0.06
    ЎыџN
    -0.06
    릭
    -0.06
    Dic
    -0.06
    reland
    -0.06
     vej
    -0.06
    POSITIVE LOGITS
     Cata
    0.07
    hydr
    0.07
    Runner
    0.07
    uae
    0.07
     CASE
    0.07
    .Char
    0.06
    imits
    0.06
     Luca
    0.06
     topl
    0.06
    oge
    0.06
    Act Density 0.008%

    No Known Activations