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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mül
    -0.08
    qd
    -0.06
     Kabul
    -0.06
     rooftop
    -0.06
     missing
    -0.06
    یف
    -0.06
     준
    -0.06
     χ
    -0.06
     dok
    -0.06
    农
    -0.06
    POSITIVE LOGITS
     пояс
    0.07
    精
    0.06
     espresso
    0.06
     turning
    0.06
     indicted
    0.06
    _PAYLOAD
    0.06
     DSM
    0.06
     уклад
    0.06
    uit
    0.06
    lock
    0.06
    Act Density 0.013%

    No Known Activations