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

    Neuronpedia

    INDEX
    Explanations

    na świad, mam włas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nije
    0.84
     треба
    0.77
     Pokud
    0.76
     imaju
    0.76
     Quando
    0.72
     nisu
    0.72
     nisam
    0.70
     škola
    0.70
     δεν
    0.69
     мають
    0.69
    POSITIVE LOGITS
    ぜひ
    0.48
     eğ
    0.47
     BLAST
    0.46
    uniformly
    0.45
    దని
    0.45
    embedded
    0.45
    compet
    0.44
    submitted
    0.44
    rating
    0.44
    attractive
    0.44
    Act Density 0.004%

    No Known Activations