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

    Neuronpedia

    INDEX
    Explanations

    /

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     RR
    -0.06
    관리
    -0.06
     привести
    -0.06
     처음
    -0.06
     причина
    -0.06
     ATT
    -0.06
    -е
    -0.06
     خان
    -0.06
     був
    -0.06
     Pierre
    -0.06
    POSITIVE LOGITS
     Hillary
    0.07
    Util
    0.06
    -avatar
    0.06
    \/
    0.06
     backyard
    0.06
    :/
    0.06
    credits
    0.06
    "/
    0.06
    stial
    0.06
     accord
    0.06
    Act Density 0.001%

    No Known Activations