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

    Neuronpedia

    INDEX
    Explanations

    code structure and function definitions in programming languages

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

    Code snippets with file paths or variables

    np_acts-logits-general · gemini-2.0-flash

    code elements and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    '}>
    -0.73
    UnknownFields
    -0.65
    theless
    -0.64
    WebServlet
    -0.61
    __':
    -0.59
    ″]
    -0.59
    ->___
    -0.58
     呢
    -0.58
    IVEREF
    -0.57
    iteiten
    -0.55
    POSITIVE LOGITS
    ,
    1.05
     InputDecoration
    0.74
    openqa
    0.61
     gravidanza
    0.59
    tagHelperRunner
    0.56
     noting
    0.54
     mattino
    0.53
     citing
    0.49
    НАЯ
    0.49
    ;
    0.49
    Act Density 0.362%

    No Known Activations