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

    Neuronpedia

    INDEX
    Explanations

    severe symptoms or resignation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     βιβ
    0.39
     संपाद
    0.39
    他們的
    0.37
    îtier
    0.37
    bra
    0.36
    izers
    0.35
     bra
    0.35
     professors
    0.35
     struktur
    0.35
     важное
    0.35
    POSITIVE LOGITS
    _"+
    0.42
    وڑا
    0.41
    deutsch
    0.41
    调制
    0.40
    ockey
    0.40
     espèce
    0.40
     доли
    0.40
    жок
    0.40
    yy
    0.39
    ("%
    0.39
    Act Density 0.000%

    No Known Activations