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

    Neuronpedia

    INDEX
    Explanations

    rel

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ich
    -0.07
    _closed
    -0.07
     пояс
    -0.07
    PackageName
    -0.06
    andaş
    -0.06
     proje
    -0.06
     ngon
    -0.06
    orange
    -0.06
    toString
    -0.06
    magnitude
    -0.06
    POSITIVE LOGITS
     uploads
    0.06
     distilled
    0.06
    ์ฟ
    0.06
     tearing
    0.06
    ARI
    0.06
    <dynamic
    0.06
    .AUTH
    0.06
     참가
    0.06
    　l
    0.06
     pilgr
    0.06
    Act Density 0.006%

    No Known Activations