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

    Neuronpedia

    INDEX
    Explanations

    field

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    бу
    -0.07
    uilder
    -0.07
    iosper
    -0.07
    กลาง
    -0.07
     夏
    -0.07
    بری
    -0.06
     impl
    -0.06
    ॉ
    -0.06
    اذا
    -0.06
    alli
    -0.06
    POSITIVE LOGITS
    \f
    0.08
     generated
    0.07
     Working
    0.07
     working
    0.07
     coordinates
    0.06
    .Input
    0.06
    ARN
    0.06
     traditions
    0.06
     poet
    0.06
     moins
    0.06
    Act Density 0.001%

    No Known Activations