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

    Neuronpedia

    INDEX
    Explanations

    long time periods

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Weekly
    -0.08
    before
    -0.08
    .week
    -0.07
    weekly
    -0.07
    Junior
    -0.07
     junior
    -0.07
    Bars
    -0.07
     motivational
    -0.07
     weekly
    -0.07
    Sections
    -0.07
    POSITIVE LOGITS
    几十
    0.09
     enseñar
    0.09
     enormous
    0.08
    中国
    0.08
    ряз
    0.08
     Animal
    0.08
     lähes
    0.08
     eternity
    0.08
     ועל
    0.08
     Carpet
    0.08
    Act Density 0.005%

    No Known Activations