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

    Neuronpedia

    INDEX
    Explanations

    the punctuation marks and section identifiers to structure the document

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

    LaTeX math symbols

    np_acts-logits-general · gemini-2.0-flash

    mathematical symbols or code delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     resourceCulture
    -0.75
     nahilalakip
    -0.67
    uxxxx
    -0.62
     betweenstory
    -0.60
     שוליים
    -0.58
     ब्रेकडाउन
    -0.58
    FunctionFlags
    -0.55
     ujednoznacz
    -0.54
     lenker
    -0.54
    richTextPanel
    -0.52
    POSITIVE LOGITS
    ReadByte
    0.44
     Tartar
    0.40
    Gross
    0.40
    Reilly
    0.39
    Check
    0.39
     bantuan
    0.39
     dostup
    0.38
    Cheers
    0.38
    ----------------
    0.38
     hoffen
    0.38
    Act Density 0.649%

    No Known Activations