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

    Neuronpedia

    INDEX
    Explanations

    drug/treatment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     puff
    -0.07
     serves
    -0.07
    ј
    -0.07
     Tent
    -0.07
     protections
    -0.07
    充足
    -0.07
     אנ
    -0.07
     meters
    -0.07
    _SCL
    -0.07
    تحميل
    -0.07
    POSITIVE LOGITS
    ITED
    0.07
     starred
    0.07
    productive
    0.07
     Wouldn
    0.07
     השנייה
    0.07
    (events
    0.06
    �
    0.06
    点赞
    0.06
    שרות
    0.06
     urllib
    0.06
    Act Density 0.016%

    No Known Activations