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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Close
    -0.07
     western
    -0.07
     fascinated
    -0.06
    .Subscribe
    -0.06
     Moon
    -0.06
    Adding
    -0.06
     paying
    -0.06
    cock
    -0.06
    伯
    -0.06
    -space
    -0.06
    POSITIVE LOGITS
     رج
    0.06
     боку
    0.06
    $url
    0.06
     Bison
    0.06
    реп
    0.06
    Pieces
    0.06
    ionage
    0.06
    杂
    0.06
    //{↵
    0.06
     güc
    0.06
    Act Density 0.023%

    No Known Activations