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

    Neuronpedia

    INDEX
    Explanations

    double

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     past
    -0.07
     envision
    -0.07
     Kern
    -0.07
    �
    -0.06
     scant
    -0.06
     Kart
    -0.06
     Feng
    -0.06
     MEN
    -0.06
     env
    -0.06
     Vista
    -0.06
    POSITIVE LOGITS
     double
    0.16
    double
    0.13
    	double
    0.13
     Double
    0.12
    Double
    0.12
     doubles
    0.10
    (double
    0.10
    	Double
    0.09
     doubled
    0.09
    -double
    0.09
    Act Density 0.018%

    No Known Activations