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

    Neuronpedia

    INDEX
    Explanations

    specificity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     luật
    -0.07
    šší
    -0.06
     Discounts
    -0.06
    =k
    -0.06
    /Input
    -0.06
    Day
    -0.06
     عملية
    -0.06
     lodge
    -0.06
     Motorcycle
    -0.06
     Cruz
    -0.06
    POSITIVE LOGITS
    IGGER
    0.07
    ):
↵
↵
    0.06
    ES
    0.06
     %+
    0.06
    atories
    0.06
     ресурс
    0.06
    ")
↵
↵
    0.06
    tol
    0.06
    ↵    
↵
    0.06
     cohort
    0.06
    Act Density 0.085%

    No Known Activations