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

    Neuronpedia

    INDEX
    Explanations

    cyrillic, german, and latin script endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ot
    0.43
    ap
    0.40
    et
    0.36
    ab
    0.35
    ast
    0.35
    ang
    0.34
    geç
    0.33
    ay
    0.33
    on
    0.33
    ar
    0.32
    POSITIVE LOGITS
    ים
    0.38
    ន៍
    0.36
    வும்
    0.35
    ة
    0.34
    णार
    0.33
    ють
    0.32
    एं
    0.32
    एको
    0.32
    猀
    0.32
    ться
    0.32
    Act Density 0.075%

    No Known Activations