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

    Neuronpedia

    INDEX
    Explanations

    oder

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -building
    -0.07
     investing
    -0.06
    站在
    -0.06
    撬
    -0.06
     wire
    -0.06
    pid
    -0.06
    哓
    -0.06
     >
    -0.06
     xây
    -0.06
    Stick
    -0.06
    POSITIVE LOGITS
    atoire
    0.08
    有必要
    0.07
     связ
    0.06
     roles
    0.06
    _qty
    0.06
     Эт
    0.06
    ė
    0.06
    俄
    0.06
    ไป
    0.06
    лю
    0.06
    Act Density 0.001%

    No Known Activations