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

    Neuronpedia

    INDEX
    Explanations

    bad

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dimensions
    -0.07
     Hank
    -0.07
     =================================================
    -0.07
     Curry
    -0.07
     علی
    -0.06
     Benny
    -0.06
     manageable
    -0.06
    -language
    -0.06
    iddle
    -0.06
    _black
    -0.06
    POSITIVE LOGITS
    -il
    0.06
     treffen
    0.06
    BarButtonItem
    0.06
     swallowing
    0.06
    .textView
    0.06
     Marlins
    0.06
    Ethernet
    0.06
    privation
    0.06
    .GetType
    0.05
    	pthread
    0.05
    Act Density 0.031%

    No Known Activations