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

    Neuronpedia

    INDEX
    Explanations

    generally or significantly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    持續
    0.74
    기
    0.70
    一句
    0.68
    Nation
    0.68
     venant
    0.68
    賴
    0.67
    𝙴
    0.67
    𝘈
    0.66
    𝙷
    0.65
     owners
    0.65
    POSITIVE LOGITS
     Acta
    0.79
    ԁ
    0.77
    ⅾ
    0.76
    in
    0.75
     дает
    0.75
     interle
    0.73
     stipulates
    0.72
    тического
    0.71
    यों
    0.71
     만큼
    0.71
    Act Density 0.001%

    No Known Activations