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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ывает
    -0.07
    (${
    -0.07
     crib
    -0.07
    Carousel
    -0.07
    deriv
    -0.06
    :'↵
    -0.06
     했
    -0.06
    (fi
    -0.06
    Improved
    -0.06
    不知道
    -0.06
    POSITIVE LOGITS
     yi
    0.07
    _loc
    0.07
    '].$
    0.06
    azers
    0.06
    _generation
    0.06
    rut
    0.06
    elli
    0.06
    /exec
    0.06
    PART
    0.06
     scaleY
    0.06
    Act Density 0.077%

    No Known Activations