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

    Neuronpedia

    INDEX
    Explanations

    g followed by ato or emma

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ن
    2.22
    en
    2.10
    ر
    2.08
    u
    1.71
    ার
    1.70
    r
    1.63
    ир
    1.60
    л
    1.56
    ాలు
    1.54
    o
    1.46
    POSITIVE LOGITS
    ्स
    1.60
    tion
    1.53
    tz
    1.53
    ging
    1.50
    ्यारह
    1.49
    ค์
    1.46
    憬
    1.46
    ged
    1.44
    regated
    1.43
    tan
    1.40
    Act Density 0.216%

    No Known Activations