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

    Neuronpedia

    INDEX
    Explanations

    print statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ें
    0.92
    \},
    0.84
     самы
    0.84
    endTime
    0.84
    ěr
    0.80
    $}
    0.80
     orbiting
    0.79
     Rydberg
    0.79
    涘
    0.79
    endDate
    0.78
    POSITIVE LOGITS
    р
    0.89
    sels
    0.76
    mortem
    0.76
    नी
    0.76
    کس
    0.75
    ți
    0.74
    particular
    0.73
    yad
    0.73
    y
    0.72
    เสน
    0.72
    Act Density 0.205%

    No Known Activations