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

    Neuronpedia

    INDEX
    Explanations

    communications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bbox
    -0.08
     submissions
    -0.07
    MAR
    -0.06
    ]];
    -0.06
    Observers
    -0.06
     perl
    -0.06
     سام
    -0.06
    пов
    -0.06
     faç
    -0.06
     Dist
    -0.06
    POSITIVE LOGITS
     Oakland
    0.07
    alendar
    0.07
    	private
    0.06
    arendra
    0.06
     espec
    0.06
    ,tr
    0.06
    children
    0.06
    .ActionBar
    0.06
     euros
    0.06
     Cox
    0.06
    Act Density 0.139%

    No Known Activations