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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and variables in equations

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

    math indices like i, j

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للاسماء
    -0.83
     كومونز
    -0.72
    protoimpl
    -0.68
    argout
    -0.65
    WithIOException
    -0.65
     transfieras
    -0.64
     مرئيه
    -0.63
    WriteTagHelper
    -0.63
     Wikimedijinoj
    -0.62
     betweenstory
    -0.62
    POSITIVE LOGITS
    xx
    0.36
    .
    0.35
    patterns
    0.34
    cis
    0.34
    rin
    0.34
     during
    0.33
     addressed
    0.33
    in
    0.33
     personal
    0.33
     in
    0.32
    Act Density 0.239%

    No Known Activations