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

    Neuronpedia

    INDEX
    Explanations

    have

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    neighbor
    -0.07
    (cost
    -0.06
    .nan
    -0.06
     Baş
    -0.06
     priest
    -0.06
    	an
    -0.06
     Stable
    -0.06
     Emergency
    -0.06
     applications
    -0.06
     "></
    -0.06
    POSITIVE LOGITS
     ΕΛ
    0.06
     ｲ
    0.06
     Spells
    0.06
    建议
    0.06
    .Theme
    0.06
     Ital
    0.06
    Gam
    0.06
    ‌ای
    0.06
    ?></
    0.06
     Все
    0.06
    Act Density 0.104%

    No Known Activations