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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Penal
    -0.07
    оль
    -0.06
     backers
    -0.06
    祖
    -0.06
     Bren
    -0.06
     sewage
    -0.06
     μεταξύ
    -0.06
    .SET
    -0.06
     belie
    -0.06
    ヴァ
    -0.06
    POSITIVE LOGITS
    acked
    0.07
     çevir
    0.07
    (/[
    0.06
    叫
    0.06
    Georgia
    0.06
     lifestyle
    0.06
     Gamma
    0.06
    Church
    0.06
     Volunteers
    0.06
    风
    0.06
    Act Density 0.000%

    No Known Activations