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

    Neuronpedia

    INDEX
    Explanations

    special characters and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    पहरण
    0.44
    သုံးပြု
    0.43
    𝙛
    0.42
    टरनेट
    0.42
    يديو
    0.41
    ठमाडौं
    0.41
    гүнкү
    0.40
    ທ່ານ
    0.40
    सैन
    0.39
    ेलकम
    0.39
    POSITIVE LOGITS
     $\
    0.53
     N
    0.46
     middle
    0.45
     ம
    0.43
     ㅇ
    0.43
     ผ
    0.43
     O
    0.41
    芏
    0.40
     z
    0.40
     App
    0.40
    Act Density 0.000%

    No Known Activations