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

    Neuronpedia

    INDEX
    Explanations

    programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tr
    -0.06
    _blog
    -0.06
     Knee
    -0.06
    q
    -0.06
     gi
    -0.06
    Circle
    -0.06
    bach
    -0.06
     Wings
    -0.06
    .permissions
    -0.06
    -hour
    -0.06
    POSITIVE LOGITS
     çoğu
    0.07
    わたし
    0.07
    дая
    0.07
    наче
    0.06
    shi
    0.06
     comun
    0.06
    ulaire
    0.06
     запит
    0.06
    щі
    0.06
     Meg
    0.06
    Act Density 0.008%

    No Known Activations