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

    Neuronpedia

    INDEX
    Explanations

    .io and .com domains

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     in
    0.33
    2
    0.31
    ED
    0.26
     an
    0.25
    在
    0.25
    of
    0.24
    s
    0.23
    SH
    0.23
     not
    0.23
     at
    0.22
    POSITIVE LOGITS
    يته
    0.27
    ו
    0.27
    $-$,
    0.25
    其他
    0.23
     كريم
    0.23
     फॉर
    0.23
    ين
    0.22
     obrá
    0.22
    followlike
    0.22
     существу
    0.22
    Act Density 0.000%

    No Known Activations