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

    Neuronpedia

    INDEX
    Explanations

    addressing topics or questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     a
    1.06
     in
    0.95
    ä
    0.95
    ని
    0.93
    ari
    0.90
    aría
    0.90
     اور
    0.82
    ır
    0.81
    𝙩
    0.80
     سبب
    0.80
    POSITIVE LOGITS
    n
    1.52
    सी
    1.30
    i
    1.28
    ל
    1.28
    У
    1.24
    on
    1.22
    al
    1.16
    ון
    1.13
    p
    1.13
    ם
    1.12
    Act Density 0.061%

    No Known Activations