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

    Neuronpedia

    INDEX
    Explanations

    references to components and substitutions in various contexts

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

    concrete examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ͠
    -0.41
    :✨
    -0.40
     Réponses
    -0.36
    PopupMenu
    -0.36
    мум
    -0.35
     repeats
    -0.34
    InitStructure
    -0.34
     Wachs
    -0.34
    Fingerprint
    -0.34
     Continuity
    -0.33
    POSITIVE LOGITS
    UnusedPrivate
    0.58
    पया
    0.52
    SourceChecksum
    0.51
    Personensuche
    0.50
     wireType
    0.49
    findpost
    0.45
    下载附件
    0.45
    infan
    0.43
     препратки
    0.43
    extAlignment
    0.43
    Act Density 0.050%

    No Known Activations