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

    Neuronpedia

    INDEX
    Explanations

    references to prominent or notable names and individuals

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

    names and reputation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    umbai
    -0.46
    ydney
    -0.42
    fähigkeit
    -0.41
     Purpose
    -0.40
    vermögen
    -0.40
     purpose
    -0.40
    :✨
    -0.39
     Kere
    -0.39
    Feign
    -0.39
    UnusedPrivate
    -0.39
    POSITIVE LOGITS
    utilisons
    0.59
     تضيفلها
    0.57
    complexContent
    0.52
    principalColumn
    0.52
     informée
    0.47
     ujednoznacz
    0.47
    Manbalar
    0.46
    Kaynakça
    0.46
     esprits
    0.46
    Hentet
    0.45
    Act Density 0.011%

    No Known Activations