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

    Neuronpedia

    INDEX
    Explanations

    break, broken, breakdown

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    రికి
    0.99
     بچ
    0.92
     Kabul
    0.87
     Money
    0.83
     money
    0.79
     kucing
    0.78
    arket
    0.78
     pigs
    0.78
     conoscenze
    0.78
    imdi
    0.77
    POSITIVE LOGITS
    cies
    0.97
    hearted
    0.94
    TestCase
    0.90
    ड्या
    0.86
    tamb
    0.85
    pear
    0.84
     слов
    0.83
     Broken
    0.82
     breaks
    0.82
     Manifesto
    0.82
    Act Density 0.171%

    No Known Activations