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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases and uncertainty in statements

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

    I don't know or it depends

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    elemField
    -0.41
     pleaſure
    -0.38
     acrylique
    -0.33
     opér
    -0.33
    MethodManager
    -0.33
     murale
    -0.32
     seru
    -0.32
    etzt
    -0.31
    vece
    -0.30
     resto
    -0.29
    POSITIVE LOGITS
    ########.
    0.69
    +#+#
    0.59
     שוליים
    0.57
     informée
    0.55
     دیکھیے
    0.51
    Hmmm
    0.50
    URLException
    0.50
    Билгалдахарш
    0.49
    Sugges
    0.49
     inconclusive
    0.48
    Act Density 0.279%

    No Known Activations