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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gaussian
    -0.07
     Fulton
    -0.07
    る
    -0.07
     Fuj
    -0.06
     있는데
    -0.06
     Cedar
    -0.06
    ]};↵
    -0.06
     Eden
    -0.06
     Taking
    -0.06
     Contemporary
    -0.06
    POSITIVE LOGITS
    Delayed
    0.07
    决
    0.06
     ery
    0.06
    ニニニニ
    0.06
     شرایط
    0.06
    /start
    0.06
     skon
    0.06
     motivating
    0.06
    eleri
    0.06
    τών
    0.06
    Act Density 0.053%

    No Known Activations