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

    Neuronpedia

    INDEX
    Explanations

    references shifts repeats

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    者の
    0.81
    者
    0.80
    者が
    0.79
    বায়
    0.79
    ნენ
    0.78
    र्गत
    0.78
    هل
    0.77
    .<
    0.77
    心态
    0.76
    보
    0.75
    POSITIVE LOGITS
     মুক্তিযুদ্ধ
    0.93
    Backspace
    0.91
     filede
    0.90
    unlink
    0.90
     Schalt
    0.89
    RetValue
    0.89
     ইন্দু
    0.88
    acco
    0.88
    ﹎
    0.84
     RetValue
    0.84
    Act Density 0.000%

    No Known Activations