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

    Neuronpedia

    INDEX
    Explanations

    explaining why or how

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    anym
    0.43
    let
    0.41
    lers
    0.39
     %><%=
    0.37
    awa
    0.37
     frowned
    0.37
    ulloch
    0.37
    qua
    0.36
    acco
    0.36
     chuyện
    0.36
    POSITIVE LOGITS
     كيف
    0.48
     如何
    0.42
    ехать
    0.39
    னுடன்
    0.39
    Ꮤ
    0.39
     fût
    0.38
     ég
    0.38
     গর্
    0.37
     എങ്ങനെ
    0.37
    如何
    0.36
    Act Density 0.016%

    No Known Activations