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

    Neuronpedia

    INDEX
    Explanations

    segments related to versioning or code generation in software documentation

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

    code comments and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     PeEnEo
    -0.98
    HtmlAttribute
    -0.82
    parsedMessage
    -0.80
    XmlAccessorType
    -0.79
    hyrchwyd
    -0.76
    MessageOf
    -0.76
    ніципа
    -0.74
    MessageTagHelper
    -0.74
    UnusedPrivate
    -0.74
     kaarangay
    -0.73
    POSITIVE LOGITS
    //
    0.32
     so
    0.29
     name
    0.28
     and
    0.27
    -
    0.27
    /*
    0.27
     names
    0.27
    ­
    0.26
     usually
    0.26
     though
    0.25
    Act Density 0.001%

    No Known Activations