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

    Neuronpedia

    INDEX
    Explanations

    list formats options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ছবিটি
    0.55
    ihe
    0.54
    otonic
    0.51
    uteur
    0.50
    കേന്ദ്രം
    0.49
     continuant
    0.49
     sefer
    0.49
    antiate
    0.48
    વાહી
    0.48
    ناول
    0.47
    POSITIVE LOGITS
    们
    0.82
    들을
    0.77
    ‌ها
    0.76
    وں
    0.75
    ѕ
    0.75
    swith
    0.74
    들은
    0.73
    들과
    0.73
    들
    0.72
    ಗಳನ್ನು
    0.71
    Act Density 0.244%

    No Known Activations