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

    Neuronpedia

    INDEX
    Explanations

    formatting and code constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :
    0.71
    ITHER
    0.61
    ﹝
    0.60
    :[/
    0.59
     custody
    0.56
     galaxies
    0.55
     ██
    0.54
    :</
    0.54
     hinsichtlich
    0.54
     (’
    0.53
    POSITIVE LOGITS
    This
    0.72
    When
    0.72
    当然
    0.68
    这项
    0.68
    Unfortunately
    0.67
     When
    0.66
     Unfortunately
    0.66
     This
    0.66
    when
    0.64
    这也
    0.64
    Act Density 0.000%

    No Known Activations