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

    Neuronpedia

    INDEX
    Explanations

    python __init__ method

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kuris
    0.45
    ...*/
    0.43
     функ
    0.43
    스가
    0.43
    FunctionName
    0.43
    왈
    0.43
     katva
    0.43
     никакого
    0.43
    時計
    0.42
     함수
    0.42
    POSITIVE LOGITS
    nd
    0.50
     holdings
    0.46
     moi
    0.45
     managing
    0.43
     Academy
    0.42
     Managing
    0.41
     Recursos
    0.40
    maar
    0.40
     với
    0.40
     Holdings
    0.40
    Act Density 0.006%

    No Known Activations