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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Black
    -0.07
    .oauth
    -0.07
    oph
    -0.07
     خاص
    -0.06
     Directorate
    -0.06
     consumer
    -0.06
     zví
    -0.06
     curriculum
    -0.06
     ICU
    -0.06
     Black
    -0.06
    POSITIVE LOGITS
    补
    0.06
     Fortunately
    0.06
    ellipsis
    0.06
    .GetFiles
    0.06
    ыв
    0.06
     이용
    0.06
     """
↵
    0.06
     může
    0.06
    ustil
    0.06
     srd
    0.06
    Act Density 0.000%

    No Known Activations