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

    Neuronpedia

    INDEX
    Explanations

    by the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    া
    1.39
    iado
    1.35
    i
    1.20
    iin
    1.15
     বলেছিলেন
    1.14
    inä
    1.14
    arap
    1.13
    imak
    1.13
    ppin
    1.12
    icho
    1.10
    POSITIVE LOGITS
     ¡
    1.25
    أل
    1.19
    僚
    1.17
    Graphical
    1.14
    theta
    1.14
     реаль
    1.10
    갑
    1.08
    Sleeping
    1.08
     нес
    1.07
    гро
    1.06
    Act Density 0.000%

    No Known Activations