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

    Neuronpedia

    INDEX
    Explanations

    sign up or registration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    مي
    0.44
    Ꮦ
    0.42
    ת
    0.42
     previs
    0.41
    лна
    0.40
    流域
    0.39
    رجع
    0.39
    ము
    0.38
    ಮಾಣ
    0.38
    퇸
    0.38
    POSITIVE LOGITS
    ot
    0.57
     a
    0.56
    ad
    0.55
    ut
    0.54
    and
    0.54
    ir
    0.53
    il
    0.53
    ant
    0.52
    ams
    0.49
    ert
    0.48
    Act Density 0.005%

    No Known Activations