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

    Neuronpedia

    INDEX
    Explanations

    expanding operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    inci
    0.46
     culture
    0.42
    NEWS
    0.42
    ulture
    0.41
     Culture
    0.40
    DNA
    0.40
    ifte
    0.40
     Transplantation
    0.40
    peza
    0.40
    ley
    0.39
    POSITIVE LOGITS
     asymptotic
    0.43
    最大限
    0.43
     originales
    0.42
    Fortunately
    0.41
     luckily
    0.40
     ORIGINAL
    0.40
    Regressor
    0.40
    ستم
    0.40
     安心
    0.40
     VERT
    0.39
    Act Density 0.004%

    No Known Activations