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

    Neuronpedia

    INDEX
    Explanations

    method calls and function definitions in a coding context

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

    Code with parentheses and semicolons

    np_acts-logits-general · gemini-2.0-flash

    code punctuation marks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyCompany
    -0.67
    bcryptjs
    -0.64
    KommentareTeilen
    -0.61
     préc
    -0.57
     genoux
    -0.56
    reactivex
    -0.56
    ValueStyle
    -0.54
    XDECREF
    -0.54
     стаття
    -0.53
     ویکی‌پدیای
    -0.52
    POSITIVE LOGITS
    évaluateur
    0.62
    ()");
    0.58
    %";
    0.56
     they
    0.56
     BoxFit
    0.54
    StateToProps
    0.54
    hdashline
    0.54
     them
    0.53
     They
    0.53
    %");
    0.52
    Act Density 0.113%

    No Known Activations