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

    Neuronpedia

    INDEX
    Explanations

    values within a range

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    裨
    0.36
    ৌম
    0.35
    க்கொ
    0.35
    ով
    0.34
    祸
    0.34
     जीवनी
    0.34
    ợ
    0.34
     செய்த
    0.33
    tkWidget
    0.32
     Vé
    0.32
    POSITIVE LOGITS
     range
    2.77
    range
    2.50
     ranges
    2.44
    Range
    2.38
     Range
    2.33
    范围
    2.31
    範囲
    2.28
     RANGE
    2.25
     диапа
    2.20
    範圍
    2.17
    Act Density 0.127%

    No Known Activations