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

    Neuronpedia

    INDEX
    Explanations

    Mathematics Subject Classification

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     winner
    -0.07
    传奇游戏
    -0.07
    全国各地
    -0.07
    _given
    -0.07
    SCRIPTOR
    -0.07
    tokenizer
    -0.07
    (canvas
    -0.07
    打仗
    -0.07
    Coordinate
    -0.07
    رياضي
    -0.06
    POSITIVE LOGITS
    rek
    0.07
     greedy
    0.07
    jection
    0.07
    spiracy
    0.06
     sólo
    0.06
     emptied
    0.06
     Alley
    0.06
    อนา
    0.06
    _Re
    0.06
    (fp
    0.06
    Act Density 0.001%

    No Known Activations