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

    Neuronpedia

    INDEX
    Explanations

    Abbreviations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    írk
    -0.06
     сторон
    -0.06
     boca
    -0.06
     cabbage
    -0.06
     bi
    -0.06
    ypical
    -0.06
     glu
    -0.06
    ismus
    -0.06
     Mer
    -0.06
    運動
    -0.06
    POSITIVE LOGITS
    ATALOG
    0.07
    Transformation
    0.06
    (Of
    0.06
    _instructions
    0.06
     --↵↵
    0.06
    igits
    0.06
     flagged
    0.06
    _each
    0.06
    ้าของ
    0.06
    NSMutableArray
    0.06
    Act Density 0.001%

    No Known Activations