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

    Neuronpedia

    INDEX
    Explanations

    demon slayer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ח
    0.66
    ำ
    0.63
    ما
    0.58
    誤差
    0.57
    ين
    0.56
    نا
    0.55
    ون
    0.52
    ాన్ని
    0.51
    疑問
    0.50
    基準
    0.49
    POSITIVE LOGITS
    :
    0.60
    ella
    0.52
    ’
    0.49
     leurs
    0.48
    raulic
    0.48
     các
    0.46
     mga
    0.46
     ujar
    0.46
    pe
    0.45
     hoher
    0.45
    Act Density 0.812%

    No Known Activations