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

    Neuronpedia

    INDEX
    Explanations

    unning/stunning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sac
    -0.07
    -db
    -0.07
    clf
    -0.07
     Liberty
    -0.07
    	rb
    -0.07
     Mac
    -0.07
     KeyValue
    -0.07
    Cro
    -0.07
    _points
    -0.06
     Fayette
    -0.06
    POSITIVE LOGITS
     stunning
    0.14
     breathtaking
    0.10
     stunned
    0.09
     Stunning
    0.08
     dazzling
    0.08
    ософ
    0.07
     staggering
    0.07
     Gunn
    0.07
     및
    0.06
    ヌ
    0.06
    Act Density 0.008%

    No Known Activations