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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     věku
    -0.07
    ��
    -0.06
     مس
    -0.06
     rahat
    -0.06
     krás
    -0.06
    τους
    -0.06
     pořad
    -0.06
     срок
    -0.06
     гол
    -0.06
     podr
    -0.06
    POSITIVE LOGITS
     discrete
    0.07
     semen
    0.06
     FIXED
    0.06
     Alias
    0.06
    .*;↵↵
    0.06
     countert
    0.06
    ngen
    0.06
     mirrored
    0.06
     SP
    0.06
    olist
    0.06
    Act Density 0.024%

    No Known Activations