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

    Neuronpedia

    INDEX
    Explanations

    tokens related to programming concepts and structure

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

    Follows "Q:" or contains unusual capitalization

    np_acts-logits-general · gemini-2.0-flash

    specific technical terms and Q&A

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ReusableCell
    -0.52
     
    -0.52
    GIVEREF
    -0.47
     extremos
    -0.47
     Sam
    -0.46
    beek
    -0.44
     paved
    -0.44
    частли
    -0.44
    macht
    -0.44
     carne
    -0.42
    POSITIVE LOGITS
    GEBURTSDATUM
    1.09
    Personensuche
    1.03
     Majefty
    0.91
     betweenstory
    0.88
     незавершена
    0.88
    protoimpl
    0.86
    tagHelperRunner
    0.83
     bezeichneter
    0.81
     ModelExpression
    0.81
     myſelf
    0.81
    Act Density 0.018%

    No Known Activations