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

    Neuronpedia

    INDEX
    Explanations

    numerical ranges

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ة
    0.73
    ק
    0.62
    น
    0.60
    an
    0.57
    ان
    0.54
    ר
    0.54
    ン
    0.52
    स
    0.52
    ع
    0.51
    ن
    0.50
    POSITIVE LOGITS
     شدید
    0.48
    emes
    0.47
    RI
    0.45
    峒
    0.44
     없고
    0.44
    MA
    0.42
    ۱
    0.41
    遒
    0.40
    種の
    0.40
    。\
    0.40
    Act Density 0.000%

    No Known Activations