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

    Neuronpedia

    INDEX
    Explanations

    alongside something else

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     κο
    0.95
     са
    0.93
     objectForKey
    0.88
    <unused209>
    0.88
    <unused670>
    0.87
     ал
    0.86
    ৬
    0.86
    ır
    0.86
     ска
    0.86
    <unused1096>
    0.85
    POSITIVE LOGITS
    (
    1.41
    ை
    1.30
    지
    1.23
    한
    1.20
    મ
    1.20
    هم
    1.17
    ش
    1.17
    an
    1.16
    es
    1.16
    ರ
    1.16
    Act Density 0.004%

    No Known Activations