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

    Neuronpedia

    INDEX
    Explanations

    planet

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     գում
    -0.11
    �ოფ
    -0.09
     цент
    -0.09
     dividing
    -0.09
     նվազ
    -0.09
     logging
    -0.08
    平方米
    -0.08
     gelegd
    -0.08
     мабла
    -0.08
    ència
    -0.08
    POSITIVE LOGITS
     Overseas
    0.08
    Typography
    0.08
     Zwei
    0.08
     II
    0.08
    inje
    0.08
     Cartoon
    0.07
     III
    0.07
     Xan
    0.07
     Toys
    0.07
     Typography
    0.07
    Act Density 0.001%

    No Known Activations