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

    Neuronpedia

    INDEX
    Explanations

    non-standard formatting and whitespace elements in structured data

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

    struct definitions and variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Grüsse
    -0.44
    startsWith
    -0.38
    InSection
    -0.38
    setVerticalGroup
    -0.38
     honour
    -0.38
    fjspx
    -0.38
     sternly
    -0.37
    enfance
    -0.37
     ladd
    -0.36
     zus
    -0.36
    POSITIVE LOGITS
    MessageOf
    0.59
    期刊论文
    0.52
    styleType
    0.46
     Roskov
    0.44
     mAdapter
    0.44
    parsedMessage
    0.44
     unknownFields
    0.44
     Exactos
    0.44
    gelopen
    0.43
    Rohy
    0.42
    Act Density 0.017%

    No Known Activations