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

    Neuronpedia

    INDEX
    Explanations

    control

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    indicator
    -0.07
     ça
    -0.07
    (rect
    -0.07
    _base
    -0.06
     Institutional
    -0.06
     Atmospheric
    -0.06
     mundane
    -0.06
     Мож
    -0.06
     DISPLAY
    -0.06
    Show
    -0.06
    POSITIVE LOGITS
    �
    0.07
    TRAN
    0.06
    FETCH
    0.06
    _level
    0.06
     tunnels
    0.06
    )])
    0.06
    别
    0.06
     břez
    0.06
    LatLng
    0.06
    /e
    0.06
    Act Density 0.020%

    No Known Activations