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

    Neuronpedia

    INDEX
    Explanations

    software code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .currentThread
    -0.07
    .Roll
    -0.06
    уск
    -0.06
     takový
    -0.06
     LOCAL
    -0.06
     inout
    -0.06
     ‌
    -0.06
    ÜM
    -0.06
    _latest
    -0.06
    abouts
    -0.06
    POSITIVE LOGITS
     dating
    0.07
     ********************************************************
    0.06
     امیر
    0.06
    Carthy
    0.06
    威
    0.06
     ix
    0.06
     Catal
    0.06
    шиб
    0.06
    brook
    0.06
     hue
    0.06
    Act Density 0.006%

    No Known Activations