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

    Neuronpedia

    INDEX
    Explanations

    final product or state

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bustling
    0.45
    åg
    0.44
     deixa
    0.44
    avanja
    0.43
     trata
    0.43
     येत
    0.43
    ensä
    0.43
    istä
    0.42
    enheim
    0.41
     তারই
    0.41
    POSITIVE LOGITS
     accidental
    0.48
    鐟
    0.45
    َت
    0.44
    窨
    0.44
    ations
    0.44
    &&\
    0.43
    上に
    0.42
    及び
    0.41
     accidentally
    0.40
    又有
    0.40
    Act Density 0.001%

    No Known Activations