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

    Neuronpedia

    INDEX
    Explanations

    specific named entities or proper nouns

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

    First word in a title or proper noun

    np_acts-logits-general · gemini-2.0-flash

    specific pairings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ValueStyle
    -1.43
     pinulongan
    -1.36
     متعلقه
    -1.18
    AnimationsModule
    -1.16
     kasarigan
    -1.13
    enumi
    -1.11
     بيها
    -1.10
    Datuak
    -1.07
    RenderAtEndOf
    -1.06
     незавершена
    -1.06
    POSITIVE LOGITS
     B
    0.60
    '
    0.60
     H
    0.55
     
    0.53
     Sch
    0.53
     tra
    0.50
     F
    0.50
    ’
    0.50
    -
    0.49
     G
    0.49
    Act Density 1.821%

    No Known Activations