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

    Neuronpedia

    INDEX
    Explanations

    pretty much anything

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     매우
    0.54
    非常に
    0.50
     অত্যন্ত
    0.50
     अत्यंत
    0.49
     بسیار
    0.47
     نہایت
    0.45
     மிகவும்
    0.44
     extremamente
    0.44
     अत्य
    0.43
     rất
    0.43
    POSITIVE LOGITS
     darn
    0.89
     damn
    0.70
     decent
    0.64
     dang
    0.61
     hefty
    0.61
     tame
    0.59
     damned
    0.58
     decently
    0.58
     straightforward
    0.58
     standard
    0.57
    Act Density 0.022%

    No Known Activations