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

    Neuronpedia

    INDEX
    Explanations

    elements likely related to time or duration

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

    Characters/symbols used as separators or in tables

    np_acts-logits-general · gemini-2.0-flash

    prisoners released or adapted

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     متعلقه
    -0.70
    Personendaten
    -0.57
     ""],
    -0.52
     */
    -0.52
    żeli
    -0.50
     pseudonym
    -0.49
     evidentemente
    -0.49
     sicuramente
    -0.49
    InjectAttribute
    -0.49
    蜒
    -0.48
    POSITIVE LOGITS
    +#+#
    0.63
    MenuInflater
    0.56
    Dış
    0.56
     CURIAM
    0.54
    jsonwebtoken
    0.54
    esserung
    0.54
    ArgumentParser
    0.52
     ministère
    0.52
    LabelTagHelper
    0.52
    Hozzáférés
    0.51
    Act Density 0.366%

    No Known Activations