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

    Neuronpedia

    INDEX
    Explanations

    numeric values and conditions in code or mathematical expressions

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

    > then

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    setVerticalGroup
    -0.47
    MLLoader
    -0.44
    ագրություններ
    -0.43
     derselbe
    -0.39
     femininas
    -0.38
     defStyle
    -0.36
    Lähteet
    -0.35
    LookAnd
    -0.34
     <>",
    -0.34
     échanges
    -0.34
    POSITIVE LOGITS
    ніципа
    0.59
     beyond
    0.53
    }>\
    0.52
     than
    0.50
    beyond
    0.48
    年以上
    0.46
     ProtoMessage
    0.46
     survival
    0.45
    IntOverflow
    0.45
    ご馳走
    0.45
    Act Density 0.097%

    No Known Activations