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

    Neuronpedia

    INDEX
    Explanations

    words related to complaints and requests

    oai_token-act-pair · gemini-2.0-flash

    "or" in different languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    windowFixed
    -0.79
     enfans
    -0.66
    seamnă
    -0.66
     démocr
    -0.65
     varmt
    -0.64
     vœux
    -0.63
     pouvoirs
    -0.63
     colorés
    -0.62
     picioare
    -0.61
     Nor
    -0.61
    POSITIVE LOGITS
     or
    1.97
    或
    1.02
     или
    1.01
     eller
    1.01
     oder
    0.89
     atau
    0.84
    หรือ
    0.84
    거나
    0.83
     o
    0.82
     یا
    0.80
    Act Density 1.635%

    No Known Activations