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

    Neuronpedia

    INDEX
    Explanations

    opening brackets and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    కు
    1.02
    <0x80>
    0.98
     be
    0.76
    قة
    0.75
    tól
    0.67
    t
    0.67
    斯科
    0.65
    ták
    0.65
    s
    0.64
    ská
    0.64
    POSITIVE LOGITS
    로
    0.95
    י
    0.93
    한
    0.82
    ’
    0.80
    ה
    0.79
    ב
    0.77
    i
    0.72
    )।
    0.71
    )’
    0.71
    その
    0.71
    Act Density 0.000%

    No Known Activations