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

    Neuronpedia

    INDEX
    Explanations

    signal processing codes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     But
    -0.07
    停车
    -0.07
    -M
    -0.07
     lethal
    -0.07
    깨
    -0.07
    (stypy
    -0.07
    LEASE
    -0.06
     QImage
    -0.06
     notices
    -0.06
    丑
    -0.06
    POSITIVE LOGITS
     analyzer
    0.07
     vej
    0.07
    lowest
    0.07
    Warm
    0.07
     jihad
    0.07
    uez
    0.07
    ניח
    0.07
     manifests
    0.06
     QVBoxLayout
    0.06
     refrigerator
    0.06
    Act Density 0.022%

    No Known Activations