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

    Neuronpedia

    INDEX
    Explanations

    book

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    INDE
    0.57
    inde
    0.48
     Нача
    0.47
     開始
    0.45
     Wrapped
    0.45
     FRAM
    0.44
     senseless
    0.44
     Генера
    0.44
    ContextHeader
    0.44
    ränkt
    0.43
    POSITIVE LOGITS
    ਣਾ
    0.43
    들이
    0.42
     solution
    0.42
    ニ
    0.41
    ructor
    0.41
    needed
    0.40
     پت
    0.40
     lab
    0.40
     totalité
    0.39
     di
    0.38
    Act Density 0.001%

    No Known Activations