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

    Neuronpedia

    INDEX
    Explanations

    punctuation, interjections, and conversational markers indicating uncertainty or continuation in dialogue

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

    institutional contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    zinho
    -0.38
     Occidente
    -0.38
     sometime
    -0.37
     Tujuan
    -0.36
     gitt
    -0.35
    föl
    -0.33
    záll
    -0.32
     bekannte
    -0.32
     least
    -0.31
    fflush
    -0.31
    POSITIVE LOGITS
    :✨
    0.71
     linkovi
    0.66
    rungsseite
    0.62
     esternos
    0.62
    expandindo
    0.60
     fieldNum
    0.57
    Rüyada
    0.56
    parsedMessage
    0.55
    0.54
    NameInMap
    0.53
    Act Density 0.096%

    No Known Activations