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

    Neuronpedia

    INDEX
    Explanations

    explaining aspects or how

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    を使う
    0.16
     파일을
    0.15
     သင်
    0.15
     ၁
    0.14
     αφού
    0.14
     অতএব
    0.14
     ɔ
    0.14
     Проци
    0.14
     ಒಳ್ಳೆಯ
    0.14
    *.
    0.14
    POSITIVE LOGITS
     aspectos
    0.25
     aspects
    0.23
    The
    0.21
     možnosti
    0.21
     the
    0.20
     zarówno
    0.20
    the
    0.20
     различные
    0.20
     peculiarities
    0.20
     how
    0.19
    Act Density 2.140%

    No Known Activations