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

    Neuronpedia

    INDEX
    Explanations

    Are you asking a question

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     स्थितियों
    1.16
     Bagi
    1.13
    ${
    1.11
     understated
    1.07
    spicuous
    1.02
     Ảnh
    0.99
    ogeneous
    0.98
     Ninety
    0.98
    alist
    0.98
     unwavering
    0.98
    POSITIVE LOGITS
    ن
    1.41
    น
    1.18
    ал
    1.16
    ਚ
    1.16
     사항
    1.12
    ष्मान
    1.11
    न
    1.10
    お客
    1.09
     suffices
    1.07
    н
    1.07
    Act Density 0.211%

    No Known Activations