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

    Neuronpedia

    INDEX
    Explanations

    visual texture

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    out
    1.13
    ی
    1.13
    ੇ
    1.05
    ə
    1.01
    irc
    0.98
    ும்
    0.96
    ہ
    0.89
    اری
    0.89
     gaseous
    0.86
     integridad
    0.84
    POSITIVE LOGITS
    ل
    1.47
    h
    1.27
     Texture
    1.23
    其他
    1.21
    ש
    1.21
    on
    1.18
    Texture
    1.16
    b
    1.16
    '
    1.11
    ع
    1.09
    Act Density 0.008%

    No Known Activations