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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and sets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    પો
    2.59
    та
    2.58
    迹
    2.36
    ﺭ
    2.35
    比如
    2.35
     тка
    2.35
    ছে
    2.28
     நாட்களில்
    2.28
    AutoScaleMode
    2.27
    𝙉
    2.27
    POSITIVE LOGITS
    ल
    3.19
    ians
    3.02
    mss
    2.97
    ל
    2.77
     اجمع
    2.61
    meng
    2.60
    น
    2.58
    هُ
    2.57
    m
    2.57
     wills
    2.54
    Act Density 0.001%

    No Known Activations