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

    Neuronpedia

    INDEX
    Explanations

    code entry point

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     yür
    -0.07
    忙
    -0.07
    _tbl
    -0.07
    湫
    -0.07
     tbl
    -0.07
     ההת
    -0.07
    陷
    -0.07
     scanning
    -0.07
    -0.07
    _al
    -0.07
    POSITIVE LOGITS
    Hat
    0.08
    achinery
    0.07
     Thể
    0.07
     dựng
    0.07
    หา
    0.07
    rapper
    0.07
    types
    0.07
     attractions
    0.07
     каждого
    0.07
    standen
    0.07
    Act Density 0.003%

    No Known Activations