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

    Neuronpedia

    INDEX
    Explanations

    fight for or against

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    reif
    1.06
    ra
    1.04
    dır
    1.02
    ul
    1.01
     Фурга
    1.01
    서는
    1.01
    ва
    0.99
    စိတ်အပိုင်း
    0.98
    মন্ত্রীর
    0.97
     Фургала
    0.95
    POSITIVE LOGITS
    เป็น
    1.25
    你
    1.23
    ه
    1.15
    จะ
    1.03
    可以
    0.97
     synthes
    0.94
    in
    0.93
    O
    0.93
     fight
    0.92
    ون
    0.91
    Act Density 0.016%

    No Known Activations