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

    Neuronpedia

    INDEX
    Explanations

    -order

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     通
    -0.07
    Physical
    -0.06
    �
    -0.06
     leo
    -0.06
     mirrors
    -0.06
     lượng
    -0.06
     smooth
    -0.06
     прок
    -0.06
    .Usuario
    -0.06
    ушка
    -0.06
    POSITIVE LOGITS
     :|:
    0.07
     muži
    0.07
     پیوند
    0.07
    ughs
    0.07
    exampleModal
    0.06
    Visibility
    0.06
    templ
    0.06
     observation
    0.06
    跳
    0.06
    азв
    0.06
    Act Density 0.000%

    No Known Activations