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

    Neuronpedia

    INDEX
    Explanations

    not

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Patterson
    -0.06
     По
    -0.06
    enes
    -0.06
    unya
    -0.06
     March
    -0.06
    八
    -0.06
     ons
    -0.06
    March
    -0.06
    Wie
    -0.06
    percent
    -0.06
    POSITIVE LOGITS
    ------------↵
    0.07
     thiệu
    0.07
     suggested
    0.07
    }>
↵
    0.06
    (':',
    0.06
    esModule
    0.06
    fontWeight
    0.06
    bero
    0.06
    #[
    0.06
    ",&
    0.06
    Act Density 0.013%

    No Known Activations