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

    Neuronpedia

    INDEX
    Explanations

    punctuation and special characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    attam
    0.47
     สี
    0.47
     anharmonic
    0.47
     हट
    0.46
     リング
    0.46
     안전
    0.45
     ทำให้
    0.45
     신경
    0.44
     Beide
    0.44
     เ
    0.43
    POSITIVE LOGITS
    })$,
    0.53
    рен
    0.45
    اق
    0.44
    و
    0.43
    피
    0.43
    到了
    0.43
    тера
    0.43
    平方
    0.43
     haystack
    0.42
    يد
    0.41
    Act Density 0.011%

    No Known Activations