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

    Neuronpedia

    INDEX
    Explanations

    sequences of repeated symbols or patterns indicative of structure in coding or documentation

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

    code separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Hyman
    -0.40
     pad
    -0.39
     noqa
    -0.38
     ActionBar
    -0.38
    rshire
    -0.36
    react
    -0.35
     comp
    -0.35
     behavior
    -0.35
    CloseOperation
    -0.34
     abdomen
    -0.34
    POSITIVE LOGITS
    ****************
    0.84
    .*")]
    0.59
    الحياه
    0.58
    ::::::::::::::::
    0.57
    ########.
    0.56
     Offisielt
    0.55
    %%%%%%%%%%%%%%%%
    0.55
    ================
    0.54
    yarnpkg
    0.54
     ligiloj
    0.54
    Act Density 0.026%

    No Known Activations