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

    Neuronpedia

    INDEX
    Explanations

    words in Arabic script

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

    Numbers or values within technical data / lists

    np_acts-logits-general · gemini-2.0-flash

    digit sequences and subsequent markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RenderAtEndOf
    -0.73
    Rüyada
    -0.71
     بيها
    -0.67
    tagHelperRunner
    -0.64
     disambiguazione
    -0.64
    Билгалдахарш
    -0.63
    rungsseite
    -0.63
    getCurrentUser
    -0.58
    openhague
    -0.57
    TagHelper
    -0.56
    POSITIVE LOGITS
    InjectAttribute
    0.57
     mijne
    0.55
     SafeMath
    0.48
     femininas
    0.47
     bodem
    0.45
     asesino
    0.45
     Escolar
    0.44
    </thead>
    0.43
     Hessian
    0.43
     térmica
    0.42
    Act Density 0.037%

    No Known Activations