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

    Neuronpedia

    INDEX
    Explanations

    references to class definitions and related attributes in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    class definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Obrázky
    -0.36
    Tracce
    -0.32
    arrêter
    -0.30
    stylers
    -0.30
     universelle
    -0.29
     aérea
    -0.29
     تكبرها
    -0.29
    żdż
    -0.28
    etc
    -0.28
     Perlu
    -0.28
    POSITIVE LOGITS
     Class
    1.13
    KURZBESCHREIBUNG
    0.74
     EconPapers
    0.73
    Class
    0.72
    indd
    0.71
     Classe
    0.71
     CLASS
    0.68
    Javadoc
    0.67
     getClass
    0.66
     وتسجيلات
    0.65
    Act Density 0.001%

    No Known Activations