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

    Neuronpedia

    INDEX
    Explanations

    structured or patterned whitespace characters possibly indicating formatting or code structure

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

    programming code and keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rmtree
    -0.39
     uitz
    -0.37
     кӀ
    -0.37
     supérieurs
    -0.37
     dirigeants
    -0.37
    hatenablog
    -0.35
    AppMethodBeat
    -0.35
    才会
    -0.35
     twórc
    -0.35
    TokenNameLBRACE
    -0.34
    POSITIVE LOGITS
    RegressionTest
    0.69
    AutoScaleMode
    0.63
    ⤹
    0.62
    Autoritní
    0.61
     pinulongan
    0.59
    SuspendLayout
    0.59
    SharedCtor
    0.59
    parsedMessage
    0.59
    expandindo
    0.59
    ViewFeatures
    0.58
    Act Density 0.008%

    No Known Activations