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

    Neuronpedia

    INDEX
    Explanations

    code-related syntax and elements in programming

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

    code and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    -0.36
     core
    -0.35
    gner
    -0.34
     class
    -0.33
    yl
    -0.33
    </h6>
    -0.32
    core
    -0.32
     region
    -0.32
    ical
    -0.32
     ه
    -0.32
    POSITIVE LOGITS
    GOTREF
    0.73
    Hentet
    0.71
     avoient
    0.70
     Autorizaciones
    0.69
    SequentialGroup
    0.69
     Autorisations
    0.68
    jsxFileName
    0.66
    AndEndTag
    0.66
     للمعارف
    0.64
     fusca
    0.63
    Act Density 0.002%

    No Known Activations