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

    Neuronpedia

    INDEX
    Explanations

    prefix data ownership

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    蹶
    0.44
    [
    0.42
    P
    0.42
    Java
    0.41
    ك
    0.41
    Π
    0.41
     nego
    0.41
    Kamu
    0.41
    Цент
    0.40
    Log
    0.39
    POSITIVE LOGITS
     افزایش
    0.47
     Confirmation
    0.46
    |_{\
    0.46
     व्यापक
    0.46
     ಅದರ
    0.46
    した場合
    0.45
     αντα
    0.44
     일반
    0.43
     ஆட்ச
    0.43
     언급
    0.43
    Act Density 0.000%

    No Known Activations