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

    Neuronpedia

    INDEX
    Explanations

    Use

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    etter
    -0.09
     Tritur
    -0.08
     Vegetarian
    -0.08
     Cooperative
    -0.08
    ómetro
    -0.08
     degrading
    -0.07
     Vigil
    -0.07
     grap
    -0.07
     voices
    -0.07
     yksi
    -0.07
    POSITIVE LOGITS
     frequent
    0.12
    频
    0.11
     frecuentes
    0.11
     eriş
    0.11
     frequently
    0.11
    requently
    0.11
     frequ
    0.10
     hızlı
    0.10
     frecuente
    0.10
     fréqu
    0.10
    Act Density 0.018%

    No Known Activations