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

    Neuronpedia

    INDEX
    Explanations

    function call expressions and their structure

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

    Code snippets with parentheses and bracket pairs

    np_acts-logits-general · gemini-2.0-flash

    code testing and analysis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Vidite
    -0.74
     Efq
    -0.69
    MessageOf
    -0.66
     الرياضيه
    -0.63
     occafion
    -0.60
     fubject
    -0.58
    EndGlobalSection
    -0.58
    addCriterion
    -0.58
    bootstrapcdn
    -0.58
     pleaſure
    -0.57
    POSITIVE LOGITS
     async
    0.75
    async
    0.63
     EconPapers
    0.55
    //
    0.54
     kasarigan
    0.52
    oforte
    0.52
    lloworld
    0.50
    schmidt
    0.49
    ession
    0.48
    PullParser
    0.47
    Act Density 0.040%

    No Known Activations