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

    Neuronpedia

    INDEX
    Explanations

    Medical terms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     confisc
    -0.06
    Second
    -0.06
     ви
    -0.06
     Reference
    -0.06
    001
    -0.06
     match
    -0.06
     Sean
    -0.06
     Macros
    -0.06
    Customer
    -0.06
     پیام
    -0.06
    POSITIVE LOGITS
     Stra
    0.07
    льт
    0.07
     deset
    0.07
     доп
    0.06
    >tagger
    0.06
    оро
    0.06
     prostitu
    0.06
     earners
    0.06
    	Z
    0.06
    ,sum
    0.06
    Act Density 0.065%

    No Known Activations