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

    Neuronpedia

    INDEX
    Explanations

    Course descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Contest
    -0.07
    Median
    -0.07
    (S
    -0.07
     passage
    -0.07
    OwnerId
    -0.06
    ань
    -0.06
     Bog
    -0.06
     Maker
    -0.06
     sectors
    -0.06
    rian
    -0.06
    POSITIVE LOGITS
    سد
    0.07
    userService
    0.07
    مة
    0.06
     kendisine
    0.06
    堂
    0.06
    �
    0.06
    ỗng
    0.06
    ýv
    0.06
    ('__
    0.06
     vậy
    0.06
    Act Density 0.003%

    No Known Activations