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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Wired
    -0.07
     haired
    -0.07
    yw
    -0.06
     boy
    -0.06
     sul
    -0.06
    EditingController
    -0.06
     racks
    -0.06
    herits
    -0.06
     minded
    -0.06
    thed
    -0.06
    POSITIVE LOGITS
    .predict
    0.07
    _mr
    0.07
     [↵
    0.06
    	camera
    0.06
    	DEBUG
    0.06
    iedy
    0.06
    //}↵
    0.06
     PTR
    0.06
     accelerometer
    0.06
    방법
    0.06
    Act Density 0.002%

    No Known Activations