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

    Neuronpedia

    INDEX
    Explanations

    ** emphasis or bolding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ్ఞ
    0.43
    amon
    0.42
     analges
    0.42
    ುಕ
    0.42
    ren
    0.41
    noxious
    0.41
    super
    0.40
    ki
    0.40
    binom
    0.40
    ன
    0.40
    POSITIVE LOGITS
    多久
    0.50
     خرا
    0.49
    ＃
    0.46
    গুলিকে
    0.46
    ですし
    0.46
    ##
    0.45
     లక్ష
    0.45
    Ƹ
    0.45
     недавно
    0.45
     Sinai
    0.44
    Act Density 0.000%

    No Known Activations