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

    Neuronpedia

    INDEX
    Explanations

    worshipping and loving God

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    狡
    0.43
     کف
    0.41
     زخم
    0.40
    ϡ
    0.40
     प्रथ
    0.38
     خلاف
    0.37
     anima
    0.37
     हिंदु
    0.37
    残酷
    0.37
    噪音
    0.36
    POSITIVE LOGITS
     Implicit
    0.43
    pointers
    0.42
    chsler
    0.41
    Implicit
    0.40
    शेष
    0.40
    Cogn
    0.39
     Bal
    0.38
     ইমেজ
    0.38
    Bal
    0.38
    이버
    0.38
    Act Density 0.006%

    No Known Activations