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

    Neuronpedia

    INDEX
    Explanations

    parentheses at start of code blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     capazes
    0.50
    bandingan
    0.49
    ព័
    0.48
     capaz
    0.47
     फीचर्स
    0.47
     konsumen
    0.47
    ונות
    0.47
    ان
    0.46
     capaces
    0.46
    ے۔
    0.46
    POSITIVE LOGITS
     circular
    0.50
     rectangular
    0.50
    畫
    0.49
     horoscope
    0.48
     MSA
    0.46
     Gospel
    0.46
     COLLATE
    0.45
     judicial
    0.45
     columnName
    0.45
     newest
    0.45
    Act Density 0.001%

    No Known Activations