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

    Neuronpedia

    INDEX
    Explanations

    probabilistic models

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Lazar
    -0.07
    野
    -0.07
     Might
    -0.06
     tighter
    -0.06
    ปรา
    -0.06
    太多了
    -0.06
     solemn
    -0.06
     hiçbir
    -0.06
    菲
    -0.06
    oman
    -0.06
    POSITIVE LOGITS
     purported
    0.07
    ㋥
    0.07
     proponents
    0.07
    conditions
    0.07
     invented
    0.07
    Enabled
    0.07
     venues
    0.07
    著名
    0.06
    ю
    0.06
     "'"
    0.06
    Act Density 0.043%

    No Known Activations