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

    Neuronpedia

    INDEX
    Explanations

    data transformation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     luder
    -0.08
    !
    -0.07
     Hein
    -0.07
    єн
    -0.07
    Bulk
    -0.07
     JsonRequest
    -0.07
     ry
    -0.07
    <(
    -0.07
     CET
    -0.06
    "is
    -0.06
    POSITIVE LOGITS
    енсив
    0.06
    IBUTES
    0.06
     MODIFY
    0.06
     실�
    0.06
     dropping
    0.06
    家族
    0.06
     tomb
    0.06
     decrease
    0.05
     sacrificing
    0.05
    ินค
    0.05
    Act Density 0.082%

    No Known Activations