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

    Neuronpedia

    INDEX
    Explanations

    elements related to various languages and scripts

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

    arabic, japanese, code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     transición
    -0.50
     bahía
    -0.48
     Turquía
    -0.47
     desierto
    -0.46
     felicitación
    -0.45
     Khusus
    -0.44
     Connectez
    -0.44
     orientación
    -0.44
     Ejecutivo
    -0.44
     barrera
    -0.44
    POSITIVE LOGITS
    DoubleQuotes
    0.61
     autorytatywna
    0.54
    transQ
    0.51
    +#+#
    0.48
     informée
    0.46
     VY
    0.46
    RunWith
    0.46
     undes
    0.45
     sw
    0.45
     scl
    0.45
    Act Density 0.290%

    No Known Activations