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

    Neuronpedia

    INDEX
    Explanations

    machine learning analysis and models

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     veulent
    0.99
     criaturas
    0.93
    Messaging
    0.91
     qualcuno
    0.90
     creepy
    0.90
     extranjeros
    0.88
     আপনার
    0.87
     você
    0.86
     quieres
    0.85
     nevoia
    0.85
    POSITIVE LOGITS
     obtained
    1.28
     employing
    1.11
     outperforms
    1.10
     applied
    1.08
     predicts
    1.08
     using
    1.06
     coupled
    1.04
     utilizing
    1.02
    を用いた
    1.02
     averaged
    1.02
    Act Density 0.565%

    No Known Activations