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

    Neuronpedia

    INDEX
    Explanations

    running and marathons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    패
    -0.06
    佳
    -0.06
    .Add
    -0.06
    머
    -0.06
     Penny
    -0.06
     Ky
    -0.06
     waiting
    -0.06
     mechanism
    -0.06
     congressional
    -0.06
    .re
    -0.06
    POSITIVE LOGITS
    unicip
    0.07
     klub
    0.07
     üç
    0.07
     bằng
    0.06
     cruz
    0.06
     Alumni
    0.06
     bev
    0.06
     abolish
    0.06
    ']");↵
    0.06
     translated
    0.06
    Act Density 0.054%

    No Known Activations