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

    Neuronpedia

    INDEX
    Explanations

    html

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .groups
    -0.07
     mars
    -0.06
    amt
    -0.06
    809
    -0.06
    irty
    -0.06
    876
    -0.06
    pios
    -0.06
    YPES
    -0.06
     autour
    -0.06
    regor
    -0.06
    POSITIVE LOGITS
    려요
    0.08
     recher
    0.07
     )↵
    0.07
     Χ
    0.06
     ま
    0.06
    .А
    0.06
     ;↵
    0.06
     :↵
    0.06
     :)↵
    0.06
     ","↵
    0.06
    Act Density 0.013%

    No Known Activations