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

    Neuronpedia

    INDEX
    Explanations

    references to different editions of materials or publications

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

    edition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     psicológico
    -0.55
     pinulongan
    -0.49
     mauvaise
    -0.48
     fiscales
    -0.45
     ainfi
    -0.45
     psicológica
    -0.44
     chrétien
    -0.44
     Turquie
    -0.43
     salariés
    -0.43
     prêtres
    -0.43
    POSITIVE LOGITS
     edition
    2.14
     Edition
    1.98
    edition
    1.86
     EDITION
    1.83
    Edition
    1.80
     editions
    1.77
     Editions
    1.42
     édition
    1.23
     edição
    1.22
     edición
    1.16
    Act Density 0.006%

    No Known Activations