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

    Neuronpedia

    INDEX
    Explanations

    heavily reliance on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     На
    0.63
    ну
    0.62
    м
    0.62
    ک
    0.58
     Те
    0.57
    IgnoreCase
    0.57
    すべての
    0.57
    ಧ
    0.56
    ە
    0.56
    ू
    0.55
    POSITIVE LOGITS
    on
    1.02
    er
    0.82
    in
    0.71
    us
    0.67
    i
    0.66
    og
    0.65
    ang
    0.65
    have
    0.63
    )
    0.62
    onk
    0.61
    Act Density 0.335%

    No Known Activations