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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and operations in a formal context

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

    Code or symbols within mathematical expressions

    np_acts-logits-general · gemini-2.0-flash

    PLURAL_CATEGORY

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Wyman
    -0.79
     Kazan
    -0.68
     Kirkwood
    -0.66
     Rasmus
    -0.64
     lant
    -0.64
     مرئيه
    -0.64
     Bryant
    -0.63
     Luciano
    -0.63
     Gorman
    -0.62
     Darryl
    -0.61
    POSITIVE LOGITS
     Oppen
    0.70
     Preston
    0.68
    AndEndTag
    0.67
     Henderson
    0.66
    Preston
    0.66
     Alembic
    0.64
     Kendra
    0.63
     ddelweddau
    0.61
     AssemblyCulture
    0.60
    Rab
    0.60
    Act Density 1.231%

    No Known Activations