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

    Neuronpedia

    INDEX
    Explanations

    non-English text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Nets
    0.42
    无线
    0.42
    ைகளை
    0.42
    造成
    0.41
     netted
    0.41
    ாதி
    0.41
     oğ
    0.40
     কর
    0.40
     delineated
    0.40
     lashed
    0.40
    POSITIVE LOGITS
    នៃ
    0.54
    ए
    0.52
    ق
    0.51
    최
    0.49
    ف
    0.49
    અ
    0.49
    ج
    0.48
    의
    0.48
    ك
    0.47
    los
    0.46
    Act Density 0.009%

    No Known Activations