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

    Neuronpedia

    INDEX
    Explanations

    code punctuation

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     부분을
    0.74
    Domain
    0.71
     çizg
    0.70
    Dress
    0.69
    рифт
    0.69
     Dress
    0.68
     bimestre
    0.66
    MART
    0.65
     Ninh
    0.64
     હત્યા
    0.64
    POSITIVE LOGITS
     nags
    0.65
     reg
    0.63
     przec
    0.62
     gọn
    0.61
     به‌عنوان
    0.59
     ex
    0.58
     sayang
    0.57
     रक्षा
    0.56
     যাতে
    0.56
     conserve
    0.56
    Act Density 0.042%

    No Known Activations