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

    Neuronpedia

    INDEX
    Explanations

    translations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     yar
    -0.07
     आक
    -0.07
    /pi
    -0.06
    Tau
    -0.06
    $field
    -0.06
     суп
    -0.06
    ゥ
    -0.06
     tk
    -0.06
     лю
    -0.06
    !--
    -0.06
    POSITIVE LOGITS
    (decoded
    0.07
     ((__
    0.07
    (using
    0.07
     restoration
    0.06
    oding
    0.06
     senin
    0.06
    able
    0.06
     Về
    0.06
    incer
    0.06
    ements
    0.06
    Act Density 0.033%

    No Known Activations