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

    Neuronpedia

    INDEX
    Explanations

    how it is used

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    整理
    0.76
     procuring
    0.75
     transforms
    0.73
    獲
    0.72
    ますが
    0.72
     ताब्यात
    0.72
    处理
    0.71
    లేదు
    0.71
     cenderung
    0.71
     конечно
    0.70
    POSITIVE LOGITS
     used
    1.64
     Used
    1.53
    用来
    1.42
    Used
    1.41
    用于
    1.41
     utilisés
    1.38
     usados
    1.36
     usado
    1.34
    used
    1.34
     usadas
    1.32
    Act Density 0.211%

    No Known Activations