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

    Neuronpedia

    INDEX
    Explanations

    phrases related to light and shadow imagery

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

    light reflection and color

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    horloge
    -0.41
     pessoais
    -0.40
    totalPages
    -0.39
     Athene
    -0.39
     biß
    -0.38
    endaft
    -0.36
     máscaras
    -0.35
     Gegenteil
    -0.34
     ماش
    -0.34
     tvrd
    -0.34
    POSITIVE LOGITS
    SequentialGroup
    0.59
    XmlAccessType
    0.59
     مشين
    0.54
     unknownFields
    0.52
     EconPapers
    0.50
     فريبيس
    0.48
     препратки
    0.48
     light
    0.47
    featureID
    0.47
    хьтан
    0.47
    Act Density 0.070%

    No Known Activations