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

    Neuronpedia

    INDEX
    Explanations

    before

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    合理性
    -0.07
    깥
    -0.07
    orts
    -0.07
     운영
    -0.07
    полнен
    -0.07
    신청
    -0.07
    "))
    -0.07
    -mod
    -0.07
    stackoverflow
    -0.07
    זמנים
    -0.07
    POSITIVE LOGITS
    [label
    0.07
     connectivity
    0.07
     exciting
    0.07
    пу
    0.07
    cake
    0.07
     stringWithFormat
    0.07
    'int
    0.07
    靶
    0.07
    .robot
    0.07
     fabrication
    0.07
    Act Density 0.012%

    No Known Activations