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

    Neuronpedia

    INDEX
    Explanations

    fashion trends

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Julian
    -0.07
     Copies
    -0.07
     Kaiser
    -0.07
     shock
    -0.06
    _days
    -0.06
     exquisite
    -0.06
    (Test
    -0.06
     canopy
    -0.06
    _suffix
    -0.06
     broccoli
    -0.06
    POSITIVE LOGITS
     goals
    0.07
    <>↵
    0.07
     Zambia
    0.07
     día
    0.06
    />↵↵
    0.06
     않
    0.06
    istry
    0.06
     rug
    0.06
     Мі
    0.06
    ोड़
    0.06
    Act Density 0.006%

    No Known Activations