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

    Neuronpedia

    INDEX
    Explanations

    references to theories and structured testing in programming

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

    coding contexts and tools

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.62
    ValueStyle
    -0.59
    MLLoader
    -0.58
     فريبيس
    -0.54
     BoxFit
    -0.53
     BoxDecoration
    -0.53
    EndContext
    -0.53
     informée
    -0.53
    WireFormatLite
    -0.52
    getDoctrine
    -0.52
    POSITIVE LOGITS
    futbolista
    0.39
    stories
    0.39
    parametrize
    0.37
     story
    0.37
    story
    0.36
     Anbau
    0.35
    engesch
    0.34
     preview
    0.33
     céu
    0.33
     récon
    0.33
    Act Density 0.022%

    No Known Activations