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

    Neuronpedia

    INDEX
    Explanations

    quotation marks and other punctuation marks indicating dialogue or text citations

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

    preceding titles of publications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ProtoMessage
    -0.59
    XmlType
    -0.57
    Microkernel
    -0.55
    ディネート
    -0.52
     EconPapers
    -0.52
    ViewFeatures
    -0.52
    writeFieldEnd
    -0.52
    disposing
    -0.50
    InitVars
    -0.50
     iconLine
    -0.50
    POSITIVE LOGITS
     getattr
    0.40
    getattr
    0.39
    awtextra
    0.38
     magist
    0.35
    ValueStyle
    0.34
    <_>
    0.32
    ⁡
    0.32
     Keen
    0.31
    Keen
    0.31
    exact
    0.31
    Act Density 0.030%

    No Known Activations