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

    Neuronpedia

    INDEX
    Explanations

    parenthetical references or annotations in a document

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

    Text inside parentheses

    np_acts-logits-general · gemini-2.0-flash

    statistics and counts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ruptedException
    -0.59
    Hentet
    -0.57
    ็บ
    -0.56
    Naissance
    -0.56
    etheless
    -0.55
     trône
    -0.54
    keiten
    -0.53
     Inters
    -0.53
     Bros
    -0.52
     electroly
    -0.52
    POSITIVE LOGITS
     using
    0.69
    Extinguishing
    0.67
     being
    0.65
     running
    0.65
     helping
    0.62
     reflecting
    0.61
     making
    0.61
     serving
    0.60
     spending
    0.59
    humidité
    0.57
    Act Density 0.454%

    No Known Activations