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

    Neuronpedia

    INDEX
    Explanations

    flute solo

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     I
    0.96
    м
    0.86
    I
    0.83
    م
    0.82
    ی
    0.78
    ς
    0.74
    ین
    0.72
    নিজ
    0.70
    อ
    0.70
    이
    0.70
    POSITIVE LOGITS
    。
    0.88
     Chlorine
    0.61
    笛
    0.60
    ране
    0.59
    bl
    0.58
     Been
    0.58
    。\
    0.58
     whistle
    0.57
    د
    0.57
    ：
    0.57
    Act Density 0.001%

    No Known Activations