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

    Neuronpedia

    INDEX
    Explanations

    mentions of authors or contributors in a research context

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

    Following certain punctuation or symbols

    np_acts-logits-general · gemini-2.0-flash

    ter ligação

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ônicos
    -1.06
    ônico
    -1.01
     estadía
    -0.98
    êmica
    -0.92
     confiable
    -0.91
    ômico
    -0.90
    êmios
    -0.90
    ônimo
    -0.89
     afuera
    -0.87
    ônica
    -0.85
    POSITIVE LOGITS
     costes
    0.75
    ficheiro
    0.69
    fich
    0.67
     fichero
    0.65
     coger
    0.61
     vais
    0.61
     acabó
    0.58
     fiche
    0.58
     £
    0.58
    ReusableCell
    0.57
    Act Density 0.050%

    No Known Activations