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

    Neuronpedia

    INDEX
    Explanations

    invention relates to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    كشن
    0.48
    歓
    0.45
    饞
    0.44
    меч
    0.41
    pkt
    0.39
    મિંગ
    0.38
    覚え
    0.38
     обязан
    0.38
     خواہش
    0.37
    エラー
    0.37
    POSITIVE LOGITS
     provided
    0.46
     menyediakan
    0.44
    提供的
    0.43
     eng
    0.42
     ту
    0.40
     Provided
    0.40
    regar
    0.39
     liv
    0.39
     Provide
    0.39
     China
    0.39
    Act Density 0.002%

    No Known Activations