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

    Neuronpedia

    INDEX
    Explanations

    sequences of mathematical symbols and numerical expressions

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

    end of citation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     resta
    -0.42
    あた
    -0.41
    󠁴
    -0.40
    memoized
    -0.40
    etheless
    -0.39
    ➟
    -0.39
     Italijani
    -0.38
    Written
    -0.38
     Unger
    -0.38
     rest
    -0.38
    POSITIVE LOGITS
    AccessorTable
    0.55
    tagHelperRunner
    0.54
    istoitu
    0.52
    دانشنامهٔ
    0.44
    rafa
    0.43
     للاسماء
    0.43
    expandindo
    0.42
    sidemargin
    0.41
     оригіналу
    0.41
    ۜ
    0.40
    Act Density 0.168%

    No Known Activations