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

    Neuronpedia

    INDEX
    Explanations

    geological time periods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     anthropologist
    0.63
     Amir
    0.59
     ادارے
    0.58
     jasmine
    0.57
     syarat
    0.57
     quail
    0.56
     museums
    0.54
    кме
    0.54
     ayah
    0.54
     sashimi
    0.54
    POSITIVE LOGITS
    TIME
    0.57
     justo
    0.54
    Dental
    0.54
    (
    0.52
    タイム
    0.50
    ’,
    0.50
    +",
    0.49
    Floral
    0.49
    Tagged
    0.48
    OR
    0.47
    Act Density 0.008%

    No Known Activations