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

    Neuronpedia

    INDEX
    Explanations

    participate in activities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    し
    1.48
    い
    1.35
    बी
    1.23
    Р
    1.20
    کر
    1.17
    ﺮ
    1.17
    ح
    1.06
    مس
    1.02
    ма
    1.01
    सा
    1.00
    POSITIVE LOGITS
    il
    1.33
    ad
    1.25
    ap
    1.05
    al
    0.99
    ip
    0.98
     participates
    0.91
    it
    0.89
    지
    0.89
    m
    0.88
    ang
    0.88
    Act Density 0.011%

    No Known Activations