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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the underscore character

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

    require_once, require_relative

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    transQ
    -0.73
     Италијани
    -0.70
    SharedCtor
    -0.68
    Personendaten
    -0.67
     Biôgrafia
    -0.62
     transfieras
    -0.60
     avulla
    -0.59
    EndGlobalSection
    -0.59
     informée
    -0.59
     Italijani
    -0.58
    POSITIVE LOGITS
     full
    0.42
    requireNonNull
    0.42
    あら
    0.38
     chemistry
    0.36
     et
    0.36
    irit
    0.36
    thyl
    0.35
     fully
    0.34
     necessary
    0.34
     symbol
    0.34
    Act Density 0.006%

    No Known Activations