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

    Neuronpedia

    INDEX
    Explanations

    patterns of code structured in a function-like syntax

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

    code and programming syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     défin
    -0.37
     set
    -0.36
     tastes
    -0.35
     label
    -0.34
     érté
    -0.34
     definition
    -0.33
     aimez
    -0.33
     érz
    -0.33
     honor
    -0.33
     lanterna
    -0.32
    POSITIVE LOGITS
    0.77
     propOrder
    0.73
    tvguidetime
    0.68
     виправивши
    0.65
    parsedMessage
    0.63
    حياته
    0.58
     <<<<<<<<<<<<<<
    0.58
    GTCX
    0.56
    PerformLayout
    0.56
    EndContext
    0.54
    Act Density 0.022%

    No Known Activations