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

    Neuronpedia

    INDEX
    Explanations

    non-English

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Mus
    -0.07
     Pend
    -0.07
    最後
    -0.06
     nhiều
    -0.06
     rented
    -0.06
    Load
    -0.06
     между
    -0.06
     substr
    -0.06
     Das
    -0.06
     Tennis
    -0.06
    POSITIVE LOGITS
    whole
    0.07
     which
    0.07
    which
    0.06
    _customer
    0.06
    plit
    0.06
    ModelProperty
    0.06
     такого
    0.06
     xOffset
    0.06
    щи
    0.06
     successive
    0.06
    Act Density 0.012%

    No Known Activations