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

    Neuronpedia

    INDEX
    Explanations

    presenting information or findings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ä
    0.52
    都知道
    0.38
     an
    0.37
     बजाय
    0.37
    정이
    0.36
    ation
    0.36
     يتح
    0.36
     in
    0.35
     در
    0.35
    ocks
    0.35
    POSITIVE LOGITS
    i
    0.55
    ad
    0.54
    ר
    0.50
    u
    0.44
    ம்
    0.44
    have
    0.43
    ur
    0.42
    in
    0.41
    f
    0.41
    T
    0.39
    Act Density 0.206%

    No Known Activations