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

    Neuronpedia

    INDEX
    Explanations

    specific patterns and symbols related to speech and dialogue

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

    programming context or technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    LookAnd
    -0.46
     Aérea
    -0.37
    原始内容存档于
    -0.36
     paard
    -0.35
     œil
    -0.34
     oorsp
    -0.34
     ufficiali
    -0.34
     Faktoren
    -0.33
     sacerdotes
    -0.33
     publiek
    -0.32
    POSITIVE LOGITS
    BibitemShut
    0.72
     EconPapers
    0.68
    parsedMessage
    0.58
    Tikang
    0.54
     snippetHide
    0.54
     nahilalakip
    0.54
    bibfield
    0.51
     Taktlose
    0.50
     виправивши
    0.49
    Réalisation
    0.49
    Act Density 0.001%

    No Known Activations