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

    Neuronpedia

    INDEX
    Explanations

    shorts or other bottom wear

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    I
    1.32
    ม
    1.15
    E
    0.93
    та
    0.85
    O
    0.85
    ت
    0.85
    ک
    0.84
    ক
    0.83
    پ
    0.83
    ل
    0.83
    POSITIVE LOGITS
    لي
    1.10
     shorts
    1.04
    shorts
    0.88
     Shorts
    0.84
    ere
    0.77
    >∕
    0.77
    يل
    0.75
     goofy
    0.73
    iyi
    0.73
    iénd
    0.72
    Act Density 0.002%

    No Known Activations