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

    Neuronpedia

    INDEX
    Explanations

    over

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tempered
    -0.08
    ствен
    -0.07
    Gregorian
    -0.07
     wenigstens
    -0.07
     roller
    -0.07
     correr
    -0.07
     cascading
    -0.07
     realm
    -0.07
     verfol
    -0.07
     Gregorian
    -0.07
    POSITIVE LOGITS
     Yii
    0.09
     предложение
    0.09
    Yii
    0.08
    ikam
    0.08
     դրա
    0.08
     предложения
    0.08
     Bavaria
    0.08
     તેના
    0.08
     knee
    0.08
     возле
    0.08
    Act Density 0.005%

    No Known Activations