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

    Neuronpedia

    INDEX
    Explanations

    descriptions of lips

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    는
    0.84
    ה
    0.84
    ב
    0.79
    ची
    0.74
    נ
    0.73
    ת
    0.72
    च
    0.71
    る
    0.66
    は
    0.66
    จ
    0.65
    POSITIVE LOGITS
     lips
    1.13
    唇
    0.93
     Lips
    0.88
    Lips
    0.85
    kaart
    0.79
    lips
    0.77
    👄
    0.77
    ”
    0.75
     labios
    0.72
     a
    0.71
    Act Density 0.005%

    No Known Activations