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

    Neuronpedia

    INDEX
    Explanations

    iPad Pro

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MA
    0.61
    ME
    0.58
    ﮭ
    0.58
    culaire
    0.56
    ंबकीय
    0.55
    état
    0.53
    preprocessing
    0.52
    卡
    0.52
    轫
    0.52
    MATH
    0.51
    POSITIVE LOGITS
     idiots
    0.80
    นี่
    0.71
     say
    0.67
     Ars
    0.63
     ars
    0.61
     directories
    0.61
     ESO
    0.59
     goodies
    0.59
    tyle
    0.59
     Behold
    0.59
    Act Density 0.000%

    No Known Activations