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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     analytics
    -0.06
     nep
    -0.06
    ermann
    -0.06
    欢
    -0.06
    數
    -0.06
    用于
    -0.06
    adow
    -0.06
    Authorized
    -0.06
     kra
    -0.06
     boil
    -0.06
    POSITIVE LOGITS
    ?s
    0.07
    ากาศ
    0.07
     Heavenly
    0.07
     gchar
    0.07
     transmitting
    0.07
     ^
    0.06
    expo
    0.06
    _subplot
    0.06
     energie
    0.06
     (~(
    0.06
    Act Density 0.088%

    No Known Activations