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

    Neuronpedia

    INDEX
    Explanations

    XML Schema definition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    0.86
    。「
    0.68
    ۳
    0.68
     увиде
    0.63
    வ்வேறு
    0.61
    arı
    0.61
    tR
    0.59
    ۔
    0.59
    ﺻ
    0.58
    し
    0.57
    POSITIVE LOGITS
    ו
    0.88
    ס
    0.88
    2
    0.87
    ב
    0.84
    0
    0.77
    ח
    0.74
     instancias
    0.73
    m
    0.73
    as
    0.72
    ]
    0.72
    Act Density 0.006%

    No Known Activations