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

    Neuronpedia

    INDEX
    Explanations

    think step by step

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ،
    1.65
    are
    1.55
     are
    1.45
    re
    1.35
    tiin
    1.28
    te
    1.26
    s
    1.23
    ，“
    1.16
    ，
    1.16
    was
    1.15
    POSITIVE LOGITS
    ية
    1.36
    لي
    1.32
    ’
    1.30
    לה
    1.07
    ைகள்
    1.05
    शील
    1.03
     похо
    1.03
    לו
    0.99
     použit
    0.99
    ROME
    0.99
    Act Density 0.116%

    No Known Activations