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

    Neuronpedia

    INDEX
    Explanations

    function calls and associated method properties within programming or scripting code

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

    Code-related actions (run, load, create, start, perform)

    np_acts-logits-general · gemini-2.0-flash

    run, load, create, start, perform, read

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ke
    -0.55
     co
    -0.53
     k
    -0.46
     ko
    -0.44
     was
    -0.43
     ka
    -0.42
     ar
    -0.42
    '=>'
    -0.42
     ben
    -0.41
     ve
    -0.41
    POSITIVE LOGITS
     فريبيس
    0.99
    脚注の使い方
    0.88
    nloa
    0.85
     zvuky
    0.81
    WithIOException
    0.80
     <>",
    0.79
     titolata
    0.77
     (€
    0.76
     חיצוניים
    0.76
     referenties
    0.75
    Act Density 0.279%

    No Known Activations