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

    Neuronpedia

    INDEX
    Explanations

    Math after =

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ؛
    0.48
     તૈયાર
    0.41
     تیار
    0.41
     bilgiler
    0.40
     الرئيسية
    0.39
    猶
    0.39
     ಮುಂದ
    0.38
     renseignements
    0.38
     preparada
    0.38
     niezbęd
    0.38
    POSITIVE LOGITS
     misog
    0.45
    Universidad
    0.44
     perjury
    0.44
    twitter
    0.44
    ouses
    0.43
    bcrypt
    0.43
    urètre
    0.42
    ($_
    0.41
    pegno
    0.40
    Unicode
    0.40
    Act Density 0.007%

    No Known Activations