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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _q
    -0.08
    QDebug
    -0.07
     mest
    -0.07
    FN
    -0.07
     violent
    -0.06
    MC
    -0.06
    CEE
    -0.06
     seen
    -0.06
    okies
    -0.06
     mutual
    -0.06
    POSITIVE LOGITS
     количе
    0.06
     полит
    0.06
    _mirror
    0.06
     وحدة
    0.06
     จำ
    0.06
     ویکی
    0.06
     образом
    0.06
    alarına
    0.06
    ２
    0.06
     kidney
    0.06
    Act Density 0.006%

    No Known Activations