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

    Neuronpedia

    INDEX
    Explanations

    value

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     сел
    -0.07
     Dec
    -0.06
    ادة
    -0.06
    ENSE
    -0.06
    린
    -0.06
    .encode
    -0.06
    십
    -0.06
     Pract
    -0.06
    Sent
    -0.06
     RAID
    -0.06
    POSITIVE LOGITS
     vine
    0.07
     sq
    0.06
    (err
    0.06
    (PyObject
    0.06
    杨
    0.06
     hemat
    0.06
    (Z
    0.06
    도를
    0.06
     int
    0.06
     ***
    0.06
    Act Density 0.012%

    No Known Activations