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

    Neuronpedia

    INDEX
    Explanations

    beaches, vejiga

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    1.37
    ियों
    1.22
    ের
    1.11
    shen
    1.07
    sion
    1.05
    sop
    0.95
    ों
    0.95
    sodium
    0.95
    아요
    0.93
    methanol
    0.92
    POSITIVE LOGITS
    и
    1.32
    ব
    1.23
    то
    1.18
    cido
    1.18
    tt
    1.17
    ﻳ
    1.12
    أ
    1.11
    ﻧ
    1.11
    ﻟ
    1.09
    ii
    1.06
    Act Density 0.000%

    No Known Activations