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

    Neuronpedia

    INDEX
    Explanations

    Things to consider

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    вами
    -0.07
     rounds
    -0.07
     delete
    -0.07
    /dd
    -0.06
    rades
    -0.06
     fires
    -0.06
    moil
    -0.06
    (number
    -0.06
     tại
    -0.06
     quanto
    -0.06
    POSITIVE LOGITS
     chopped
    0.06
    datos
    0.06
    ibern
    0.06
     ‏
    0.06
    м
    0.06
    なかった
    0.06
     Suz
    0.06
     、
    0.06
    -vertical
    0.06
     Reserved
    0.06
    Act Density 0.148%

    No Known Activations