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

    Neuronpedia

    INDEX
    Explanations

    Select one:

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uleiro
    0.28
     spermatozoa
    0.26
    indari
    0.25
    erapia
    0.25
    dayspecial
    0.25
     colouring
    0.24
    itej
    0.24
     rumours
    0.24
     polarised
    0.24
    colours
    0.24
    POSITIVE LOGITS
     University
    0.24
    听
    0.24
    聽
    0.23
     Input
    0.21
     Well
    0.21
     ввод
    0.21
    Formula
    0.21
     Houston
    0.21
     Arkansas
    0.21
    сл
    0.21
    Act Density 0.018%

    No Known Activations