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

    Neuronpedia

    INDEX
    Explanations

    Aruch/Avraham

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    宣告
    -0.07
    (reordered
    -0.07
    챠
    -0.07
    фи
    -0.07
     helped
    -0.07
    _CheckedChanged
    -0.06
    🥘
    -0.06
    álido
    -0.06
    学员
    -0.06
    恰好
    -0.06
    POSITIVE LOGITS
     SG
    0.07
     zh
    0.07
     doğum
    0.07
     kvinner
    0.06
     Jong
    0.06
    JC
    0.06
    GS
    0.06
     Lilly
    0.06
    กฎหมาย
    0.06
     Longitude
    0.06
    Act Density 0.004%

    No Known Activations