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

    Neuronpedia

    INDEX
    Explanations

    SQL queries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hurricanes
    -0.09
    infos
    -0.09
     хорош
    -0.08
     మంచి
    -0.08
     좋은
    -0.08
    prep
    -0.08
    Detailed
    -0.08
     arsenal
    -0.08
     detall
    -0.08
    cache
    -0.08
    POSITIVE LOGITS
     بسيطة
    0.09
     Рад
    0.08
    	payload
    0.08
    .payload
    0.08
     ao
    0.08
     trivial
    0.08
     сл
    0.08
     device
    0.08
     Olaf
    0.08
     payload
    0.08
    Act Density 0.013%

    No Known Activations