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

    Neuronpedia

    INDEX
    Explanations

    listing, code, punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mici
    0.52
     /.
    0.41
     sido
    0.39
     actualidad
    0.38
     directions
    0.38
    .
    0.38
     cities
    0.37
    ).
    0.36
     sebagainya
    0.36
    。
    0.35
    POSITIVE LOGITS
    ⁸
    0.47
    ⁷
    0.47
    Conceptual
    0.46
    🫰
    0.46
    Earlier
    0.45
     యొక్క
    0.45
     структура
    0.45
    としての
    0.44
    cookieParser
    0.44
     взаимодействие
    0.44
    Act Density 0.025%

    No Known Activations