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

    Neuronpedia

    INDEX
    Explanations

    function calls and method invocations in programming code

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

    File writing or buffer operations in code

    np_acts-logits-general · gemini-2.0-flash

    writing and function calls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     queſta
    -0.70
     ſte
    -0.69
    ſelf
    -0.68
     houſe
    -0.68
     ſche
    -0.68
     ſta
    -0.68
     faſt
    -0.66
     geweſen
    -0.65
     ujednoznacz
    -0.65
    <unused3>
    -0.64
    POSITIVE LOGITS
    memberof
    0.44
    memberOf
    0.40
    styleable
    0.37
    enterOuterAlt
    0.35
    makeText
    0.33
     talaga
    0.32
    Parameteri
    0.32
     AssemblyCompany
    0.32
     us
    0.31
    بوابة
    0.31
    Act Density 0.256%

    No Known Activations