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
    chts
    -0.07
    指导
    -0.07
    749
    -0.07
     initialized
    -0.06
    -Za
    -0.06
     MSS
    -0.06
     San
    -0.06
     SAN
    -0.06
     heg
    -0.06
     IAM
    -0.06
    POSITIVE LOGITS
     sou
    0.07
    	double
    0.07
     듯
    0.07
    LOW
    0.07
     FB
    0.07
    warm
    0.06
    (conf
    0.06
    felt
    0.06
     rebuild
    0.06
     suggests
    0.06
    Act Density 0.010%

    No Known Activations