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

    Neuronpedia

    INDEX
    Explanations

    code that defines functions and commands in a programming context

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

    command execution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vantagens
    -0.43
    reness
    -0.39
     ancianos
    -0.37
    Démographie
    -0.37
    DoubleQuotes
    -0.37
     ब्रेकडाउन
    -0.36
    roek
    -0.36
    gridy
    -0.35
    Vorteile
    -0.35
     sija
    -0.35
    POSITIVE LOGITS
     command
    0.98
     commands
    0.97
    Commands
    0.97
    commands
    0.95
     Commands
    0.95
    command
    0.90
     Command
    0.90
    Command
    0.88
    COMMAND
    0.82
    命令
    0.79
    Act Density 0.061%

    No Known Activations