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

    Neuronpedia

    INDEX
    Explanations

    pathlib or Leo

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ەن
    0.68
    ങ്ങാ
    0.68
    攽
    0.65
    秧
    0.64
    煂
    0.61
    敚
    0.60
    𝕄
    0.59
    पतवार
    0.59
    顼
    0.59
     আহসান
    0.58
    POSITIVE LOGITS
     L
    2.23
     Л
    2.22
     ল
    2.22
    L
    2.20
     ல
    2.08
     ല
    2.03
     ల
    2.01
    Ｌ
    2.01
     Ло
    1.99
     ل
    1.96
    Act Density 2.504%

    No Known Activations