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

    Neuronpedia

    INDEX
    Explanations

    as the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ඔවුන්
    0.66
     других
    0.61
    बंधनाच्या
    0.57
     例えば
    0.57
    我们也
    0.57
     यासाठी
    0.56
     drugih
    0.55
     інших
    0.54
     પણ
    0.54
     (
    0.54
    POSITIVE LOGITS
    b
    0.82
    an
    0.75
    f
    0.71
    d
    0.70
    m
    0.55
    '
    0.55
    g
    0.55
    v
    0.55
    et
    0.53
     an
    0.49
    Act Density 0.471%

    No Known Activations