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

    Neuronpedia

    INDEX
    Explanations

    references to usage, configuration, and relationships in technical contexts

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

    using code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     psicológico
    -0.55
     Garantía
    -0.50
     duradero
    -0.50
     desconocido
    -0.50
     sorpresas
    -0.49
     cómodo
    -0.48
     cœurs
    -0.47
     débats
    -0.47
     establecido
    -0.46
     prohibido
    -0.46
    POSITIVE LOGITS
    ✨:
    0.53
     المعيارى
    0.52
     noDo
    0.45
    }{#
    0.45
     Hy
    0.45
     مرئيه
    0.44
     فريبيس
    0.44
     versions
    0.43
    rectangular
    0.43
     Smart
    0.43
    Act Density 0.113%

    No Known Activations