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

    Neuronpedia

    INDEX
    Explanations

    generating results

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ctime
    -0.07
    ㎡
    -0.07
     Fraser
    -0.07
     consequat
    -0.06
     feeder
    -0.06
    Optimizer
    -0.06
     Editors
    -0.06
     WHITE
    -0.06
     rallied
    -0.06
     grounds
    -0.06
    POSITIVE LOGITS
     [$
    0.07
     yemek
    0.06
     ود
    0.06
    光
    0.06
     stuff
    0.06
    ále
    0.06
    	emit
    0.06
     sodom
    0.06
    IntervalSince
    0.06
    งก
    0.06
    Act Density 0.002%

    No Known Activations