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

    Neuronpedia

    INDEX
    Explanations

    code or programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Gebäude
    -0.08
    🇧
    -0.07
    (bus
    -0.07
     jade
    -0.07
    开封
    -0.07
     Tubes
    -0.07
    xCD
    -0.07
     parsed
    -0.07
    �
    -0.07
    九州
    -0.07
    POSITIVE LOGITS
    튿
    0.08
    ('[
    0.06
    .catch
    0.06
    멂
    0.06
    ines
    0.06
     jour
    0.06
    rk
    0.06
    哪些
    0.06
    停下
    0.06
    пуск
    0.06
    Act Density 0.074%

    No Known Activations