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

    Neuronpedia

    INDEX
    Explanations

    filenames and initialization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     '.',
    0.78
     `=`
    0.74
    [],
    0.71
     histograms
    0.70
    事实上
    0.68
    motionProxy
    0.68
     omission
    0.67
     eigenvectors
    0.67
     ".")
    0.67
     "."
    0.67
    POSITIVE LOGITS
    example
    0.98
    Example
    0.98
    script
    0.97
    test
    0.92
     скри
    0.90
    Teste
    0.90
    main
    0.90
    Demo
    0.89
    exemple
    0.88
    _[
    0.87
    Act Density 0.287%

    No Known Activations