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

    Neuronpedia

    INDEX
    Explanations

    leadership roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AM
    1.18
    EN
    1.13
    IE
    1.11
    IEN
    1.07
    ON
    1.06
    ET
    1.02
    ES
    0.99
    AL
    0.98
    EPEND
    0.97
    不允许
    0.97
    POSITIVE LOGITS
    특별시
    1.23
    kring
    1.06
    dengan
    0.98
    ری
    0.98
    лно
    0.98
    ️⃣
    0.96
    ⃣
    0.94
     paio
    0.93
     keenly
    0.92
    aient
    0.91
    Act Density 0.006%

    No Known Activations