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

    Neuronpedia

    INDEX
    Explanations

    possibility

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    タン
    -0.07
     tong
    -0.07
    .picture
    -0.07
     kvinde
    -0.07
     Owen
    -0.06
    Sau
    -0.06
    (arr
    -0.06
    _permission
    -0.06
     преступ
    -0.06
    cosa
    -0.06
    POSITIVE LOGITS
     سمت
    0.07
     receiving
    0.07
    atsu
    0.07
     ADS
    0.06
    (-(
    0.06
    gart
    0.06
    .DropTable
    0.06
    asma
    0.06
     reside
    0.06
     withholding
    0.06
    Act Density 0.045%

    No Known Activations