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

    Neuronpedia

    INDEX
    Explanations

    references to specific ideas or concepts, particularly those introduced by the word "that."

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

    that is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     defaultstate
    -0.75
     arşivlendi
    -0.68
    uxxxx
    -0.62
     betweenstory
    -0.61
     '\\;'
    -0.60
    RegressionTest
    -0.59
    fromnode
    -0.55
     Paglinawan
    -0.55
    TypedDataSet
    -0.54
    tonode
    -0.52
    POSITIVE LOGITS
    nonatomic
    0.42
     concern
    0.42
     definitely
    0.40
     happens
    0.40
     can
    0.38
     must
    0.38
     cannot
    0.38
    ’
    0.36
     many
    0.36
     certainly
    0.36
    Act Density 0.035%

    No Known Activations