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

    Neuronpedia

    INDEX
    Explanations

    terms associated with modifying, changing, or editing code and configurations

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

    edit, change, modify

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.54
    ngdoc
    -0.39
     вікісторінку
    -0.34
    enderror
    -0.34
    menuStrip
    -0.33
    HandlerContext
    -0.33
    racene
    -0.33
     serotonin
    -0.33
     existence
    -0.32
    Descr
    -0.32
    POSITIVE LOGITS
    Hochspringen
    0.61
     disambiguazione
    0.61
    ########.
    0.54
    SourceChecksum
    0.54
     myſelf
    0.52
    WriteAttribute
    0.52
    GEBURTSDATUM
    0.51
     hikariConfig
    0.50
    justed
    0.50
     ſtill
    0.50
    Act Density 0.095%

    No Known Activations