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

    Neuronpedia

    INDEX
    Explanations

    numbers followed by punctuation or specific symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     telah
    0.52
    netz
    0.51
    তাহাকে
    0.51
     sillons
    0.49
    ESTER
    0.47
    তাহাদের
    0.47
     subtypes
    0.47
     estuary
    0.46
     Est
    0.46
    おはよう
    0.46
    POSITIVE LOGITS
    ية
    0.44
    ቕ
    0.44
    公正
    0.43
    állítás
    0.43
    لة
    0.43
    ारक
    0.43
    堛
    0.42
    ло
    0.42
    лед
    0.41
     النق
    0.41
    Act Density 0.001%

    No Known Activations