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

    Neuronpedia

    INDEX
    Explanations

    free

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (selector
    -0.06
    الش
    -0.06
     milieu
    -0.06
    产品
    -0.06
    に出
    -0.06
     racism
    -0.06
    MH
    -0.06
     عرضه
    -0.06
    米
    -0.06
     undes
    -0.06
    POSITIVE LOGITS
    04
    0.07
    07
    0.06
    08
    0.06
     aberr
    0.06
    (canvas
    0.06
     bude
    0.06
     sun
    0.06
    О
    0.06
     Carr
    0.06
    启动
    0.06
    Act Density 0.015%

    No Known Activations