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

    Neuronpedia

    INDEX
    Explanations

    mixarid, meclis, مصر, meows

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ovu
    0.45
     जिंद
    0.45
    ूले
    0.42
    ่ะ
    0.42
     høj
    0.41
    ົມ
    0.41
     Dez
    0.41
     høy
    0.40
    वेदनशील
    0.40
    स्तक
    0.40
    POSITIVE LOGITS
     باشد
    0.52
    باشد
    0.46
    0.45
     تواند
    0.43
     -
    0.42
    fruit
    0.41
    φ
    0.41
     f
    0.41
     شود
    0.39
     گیرد
    0.38
    Act Density 0.003%

    No Known Activations