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

    Neuronpedia

    INDEX
    Explanations

    increasing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    কাতা
    1.56
     patented
    1.52
     skillfully
    1.49
     posX
    1.48
    म्स
    1.43
    ewise
    1.42
     }^{-
    1.42
     nasty
    1.41
    comboBox
    1.40
    ྵ
    1.37
    POSITIVE LOGITS
    ز
    1.75
     pains
    1.62
    值
    1.56
    เติ
    1.53
     cường
    1.49
    Ecco
    1.43
     tenfold
    1.41
    interpol
    1.38
     apuesta
    1.38
    ashed
    1.37
    Act Density 0.387%

    No Known Activations