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

    Neuronpedia

    INDEX
    Explanations

    Code analysis tools config

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     missionary
    -0.08
    arkin
    -0.07
     UPS
    -0.07
    .div
    -0.07
    .Comm
    -0.07
    ecom
    -0.07
    �
    -0.07
    .getInt
    -0.07
     회
    -0.07
    Translation
    -0.07
    POSITIVE LOGITS
    מגוון
    0.07
    鉴
    0.07
    疑难
    0.06
    (Dense
    0.06
     exhibits
    0.06
    _BYTES
    0.06
    字符
    0.06
    黢
    0.06
     horrors
    0.06
     tight
    0.06
    Act Density 0.000%

    No Known Activations