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

    Neuronpedia

    INDEX
    Explanations

    engine

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.07
    摸
    -0.06
     ی
    -0.06
    FAILED
    -0.06
     是
    -0.06
     Nurse
    -0.06
     ​​​
    -0.06
     ο
    -0.06
    (insert
    -0.06
     RESET
    -0.06
    POSITIVE LOGITS
     naprost
    0.07
    ben
    0.07
    geben
    0.06
    ults
    0.06
    KG
    0.06
    ])+
    0.06
    POS
    0.06
    ){
    0.06
    usa
    0.06
    商品
    0.06
    Act Density 0.777%

    No Known Activations