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

    Neuronpedia

    INDEX
    Explanations

    affiliate

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    :Register
    -0.08
    .rl
    -0.07
     Richt
    -0.07
    UPPORT
    -0.07
    装甲
    -0.07
    _BP
    -0.06
    光荣
    -0.06
    KeySpec
    -0.06
    ArrayList
    -0.06
     buồn
    -0.06
    POSITIVE LOGITS
    蚆
    0.07
    情形
    0.07
     למשל
    0.07
    تع
    0.07
    \e
    0.07
    _sep
    0.06
    しております
    0.06
     umożliwia
    0.06
     четыре
    0.06
     individ
    0.06
    Act Density 0.003%

    No Known Activations