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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     patrols
    -0.06
    ルク
    -0.06
     Dün
    -0.06
    63
    -0.06
    83
    -0.06
    13
    -0.06
    카
    -0.06
    政府
    -0.06
    gone
    -0.06
     Hire
    -0.06
    POSITIVE LOGITS
     büyük
    0.07
    ũi
    0.07
     undermining
    0.07
    Courtesy
    0.06
     कथ
    0.06
     Čech
    0.06
     Johan
    0.06
     restructuring
    0.06
    "]->
    0.06
    ıyla
    0.06
    Act Density 0.054%

    No Known Activations