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

    Neuronpedia

    INDEX
    Explanations

    freecodecampsumdiscnigram

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ف
    0.40
    2
    0.37
    4
    0.36
    ورش
    0.35
    3
    0.35
    7
    0.35
    rol
    0.34
    6
    0.34
    DA
    0.33
    1
    0.33
    POSITIVE LOGITS
     Regno
    0.41
     تیار
    0.41
    لل
    0.40
     dere
    0.39
    l
    0.39
    lma
    0.39
    ্লিশ
    0.38
     naf
    0.38
    ലെസ്
    0.38
    UGUST
    0.38
    Act Density 0.134%

    No Known Activations