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

    Neuronpedia

    INDEX
    Explanations

    Islamic terms and languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    measured
    0.42
    퓨
    0.42
    ረው
    0.41
    alanya
    0.41
     Coles
    0.41
    ێ
    0.41
    strokes
    0.41
    esus
    0.40
    peas
    0.39
    ேய
    0.39
    POSITIVE LOGITS
    मत
    0.64
    ayat
    0.58
    ایت
    0.55
    ायत
    0.54
    دت
    0.54
    ادت
    0.52
    যত
    0.52
    عت
    0.51
    মত
    0.51
    ayet
    0.49
    Act Density 0.001%

    No Known Activations