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

    Neuronpedia

    INDEX
    Explanations

    vague references to time

    oai_token-act-pair · gemini-2.0-flash

    or

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    참고
    -0.81
     '\\;'
    -0.73
     transférez
    -0.71
    enzie
    -0.64
     AssemblyCulture
    -0.63
    DockStyle
    -0.63
    TintMode
    -0.62
    出版年
    -0.61
     Infórmanos
    -0.59
    امية
    -0.56
    POSITIVE LOGITS
     or
    1.18
     или
    0.79
    或
    0.76
     oder
    0.73
     so
    0.73
     atau
    0.66
    or
    0.64
     eller
    0.63
    или
    0.61
     或
    0.58
    Act Density 0.858%

    No Known Activations