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

    Neuronpedia

    INDEX
    Explanations

    function invocation patterns

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

    function call results

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personensuche
    -0.56
     '\\;'
    -0.54
     Taktlose
    -0.50
     الحره
    -0.49
    ArrowToggle
    -0.49
    wende
    -0.47
    colhead
    -0.47
    ')";
    -0.47
    enterOuterAlt
    -0.46
     PeEnEo
    -0.46
    POSITIVE LOGITS
    =$?
    0.47
     hasilnya
    0.46
     results
    0.45
     returns
    0.45
     result
    0.44
     Result
    0.43
     Returning
    0.43
     Returns
    0.43
     returned
    0.42
     sonuç
    0.42
    Act Density 0.077%

    No Known Activations