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

    Neuronpedia

    INDEX
    Explanations

    test

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Date
    -0.08
     Lyon
    -0.07
    edad
    -0.07
    ulfilled
    -0.07
    ([])↵
    -0.07
    adc
    -0.07
     donate
    -0.07
    的心态
    -0.07
    _Code
    -0.07
    Martin
    -0.07
    POSITIVE LOGITS
    specified
    0.07
    /I
    0.07
    הליכ
    0.07
     бел
    0.07
     TimeInterval
    0.06
    _primary
    0.06
    رعا
    0.06
     fired
    0.06
    /g
    0.06
    顯
    0.06
    Act Density 0.027%

    No Known Activations