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

    Neuronpedia

    INDEX
    Explanations

    ongoing conflict or situation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     It
    1.08
    ۰
    0.88
    d
    0.84
    rik
    0.84
    ravel
    0.84
     '
    0.83
     If
    0.82
    Error
    0.82
    Calories
    0.81
    <h3>
    0.80
    POSITIVE LOGITS
    ق
    1.66
    ف
    1.60
    ج
    1.45
    ي
    1.14
    지
    1.13
    კ
    1.05
    부가
    1.05
    م
    1.05
    ش
    1.01
    프
    1.01
    Act Density 0.030%

    No Known Activations