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

    Neuronpedia

    INDEX
    Explanations

    particularly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Forgery
    0.47
     Norton
    0.45
     TECHNI
    0.45
    cps
    0.45
     Dancer
    0.44
     Girl
    0.44
     Faktor
    0.44
    éviter
    0.44
     SERVICES
    0.42
     Fabrication
    0.42
    POSITIVE LOGITS
     މ
    0.50
     recaud
    0.49
     ста
    0.47
    rensa
    0.47
     са
    0.44
    multiSelectList
    0.44
     е
    0.43
     ма
    0.42
     compré
    0.42
     高級
    0.41
    Act Density 0.002%

    No Known Activations