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

    Neuronpedia

    INDEX
    Explanations

    setting or changing values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     analisi
    0.45
     રચ
    0.42
    訳
    0.42
     OP
    0.39
     مسائل
    0.39
     discriminate
    0.39
    cosec
    0.39
     ರಚ
    0.38
     المس
    0.38
     kelu
    0.38
    POSITIVE LOGITS
     değişt
    0.98
    新的
    0.98
     변경
    0.97
     تغییر
    0.96
    変更
    0.94
     পরিবর্তন
    0.93
     replacement
    0.92
    เปลี่ยน
    0.92
     replacing
    0.92
     changed
    0.90
    Act Density 0.141%

    No Known Activations