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

    Neuronpedia

    INDEX
    Explanations

    programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Through
    -0.08
    ោង
    -0.07
     spr
    -0.07
    isserie
    -0.07
    UInt
    -0.07
     speeds
    -0.07
    σ
    -0.07
    Programming
    -0.07
     mágico
    -0.07
    Hund
    -0.07
    POSITIVE LOGITS
     رفض
    0.09
     मृत्यु
    0.09
     bezel
    0.08
     касается
    0.08
    _PRESS
    0.08
    razi
    0.08
     OS
    0.08
     ملك
    0.08
     Essay
    0.08
     réfléch
    0.08
    Act Density 0.002%

    No Known Activations