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

    Neuronpedia

    INDEX
    Explanations

    versions of the Apache License

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

    Version 2.0

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     disambiguazione
    -0.61
     utafitiHapana
    -0.53
    orianCalendar
    -0.53
    adpleegd
    -0.53
     propOrder
    -0.52
    nestjs
    -0.50
    SharedCtor
    -0.49
     coron
    -0.49
    izations
    -0.49
    irvana
    -0.48
    POSITIVE LOGITS
     siècles
    0.39
     fidé
    0.33
     îles
    0.32
     esprits
    0.32
     acuerdos
    0.31
     wireType
    0.31
     âmes
    0.31
    httphttps
    0.30
    Hochspringen
    0.30
     Salle
    0.29
    Act Density 0.003%

    No Known Activations