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

    Neuronpedia

    INDEX
    Explanations

    ins

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    HK
    -0.07
     عشر
    -0.07
    119
    -0.07
     Prediction
    -0.06
    AYER
    -0.06
     preg
    -0.06
     exponential
    -0.06
    domain
    -0.06
     invariant
    -0.06
     ог
    -0.06
    POSITIVE LOGITS
     تنظیم
    0.06
     writeFile
    0.06
     sust
    0.06
     položky
    0.06
     图
    0.06
     sü
    0.06
     prefetch
    0.06
    荒
    0.06
    _Renderer
    0.06
    ские
    0.06
    Act Density 0.116%

    No Known Activations