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

    Neuronpedia

    INDEX
    Explanations

    variable assignment and return statements in code

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

    return value assignments or usages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    دانشنامهٔ
    -0.75
    UserScript
    -0.75
    IntoConstraints
    -0.73
    цездатний
    -0.67
     AssemblyCompany
    -0.65
    ſelf
    -0.63
     ſind
    -0.61
    webElementXpaths
    -0.60
     betweenstory
    -0.57
     pleaſure
    -0.57
    POSITIVE LOGITS
     ret
    1.29
    ret
    1.23
    Ret
    1.06
     Ret
    1.00
     return
    0.81
    retval
    0.77
    retVal
    0.75
     retval
    0.75
    RET
    0.75
     RET
    0.75
    Act Density 0.006%

    No Known Activations