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

    Neuronpedia

    INDEX
    Explanations

    civil engineering, rights, war, resistance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ла
    1.29
    ся
    1.20
    ות
    1.20
    ن
    1.20
    ي
    1.19
    ન
    1.17
    י
    1.13
    لي
    1.11
    ti
    1.10
    い
    1.10
    POSITIVE LOGITS
    <0x80>
    1.08
    _
    1.04
    Civil
    1.02
    ０
    1.01
    <
    0.98
    0
    0.97
    >
    0.97
    ).”
    0.88
    ۰
    0.85
    You
    0.82
    Act Density 0.006%

    No Known Activations