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

    Neuronpedia

    INDEX
    Explanations

    splitting text and data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    لی
    0.74
    مانی
    0.61
    ;
    0.61
    می
    0.61
     aspek
    0.58
    Testing
    0.57
    Man
    0.56
    ده
    0.56
    در
    0.55
    Sleep
    0.55
    POSITIVE LOGITS
    文字列
    0.79
    字符串
    0.79
    ቱን
    0.67
     платы
    0.64
     покупать
    0.62
     antigua
    0.59
     string
    0.58
     ridiculus
    0.58
     righth
    0.57
     второй
    0.57
    Act Density 0.350%

    No Known Activations