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

    Neuronpedia

    INDEX
    Explanations

    flash, javascript, fiction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    л
    3.03
    нга
    2.58
    нды
    2.44
    ти
    2.44
     leche
    2.30
    н
    2.23
    תה
    2.21
     причем
    2.13
     convolutional
    2.09
    з
    2.04
    POSITIVE LOGITS
    ی
    2.24
    dropout
    2.15
    ामुळे
    2.14
    िक
    2.13
    ऐ
    2.12
    وأ
    2.03
    ക
    2.02
    க்கு
    2.01
     pretty
    2.01
    pretty
    2.00
    Act Density 0.162%

    No Known Activations