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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dam
    -0.07
    -М
    -0.06
     cez
    -0.06
     agrees
    -0.06
    inyin
    -0.06
     Tops
    -0.06
     streak
    -0.06
    (driver
    -0.06
    ị
    -0.05
    Wifi
    -0.05
    POSITIVE LOGITS
     参数
    0.07
     celebrities
    0.07
    Patients
    0.06
     míst
    0.06
     Patients
    0.06
    アル
    0.06
    traction
    0.06
     appearance
    0.06
    τουργ
    0.06
     monde
    0.06
    Act Density 0.008%

    No Known Activations