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

    Neuronpedia

    INDEX
    Explanations

    references to mathematical notation and coding syntax

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

    academic references and structure names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.52
    awtextra
    -0.50
     Könige
    -0.42
    bitkan
    -0.39
     diseñadores
    -0.37
     zaby
    -0.36
     enfans
    -0.35
    arraycopy
    -0.33
     campañas
    -0.32
     /\.
    -0.32
    POSITIVE LOGITS
    ngdoc
    0.68
    存于互联网档案馆
    0.62
     relationship
    0.62
     whofe
    0.60
     description
    0.58
     information
    0.58
    읗
    0.57
    WireFormatLite
    0.55
     anſ
    0.55
     geſch
    0.55
    Act Density 0.399%

    No Known Activations