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

    Neuronpedia

    INDEX
    Explanations

    make the or your

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    醫
    0.42
     ゼ
    0.40
    ケーブル
    0.39
     CCCC
    0.39
     buen
    0.39
    electronics
    0.39
    ط
    0.39
     outcast
    0.38
    оз
    0.38
     ISP
    0.38
    POSITIVE LOGITS
    urbation
    0.44
     పరిస్థి
    0.42
     ተመሳሳይ
    0.41
    越来越多的
    0.41
    émi
    0.41
     rozwiąz
    0.40
    плення
    0.40
    馊
    0.40
    సారి
    0.40
    提高
    0.39
    Act Density 0.005%

    No Known Activations