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

    Neuronpedia

    INDEX
    Explanations

    income tax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    notch
    0.83
     Tuple
    0.76
    OREM
    0.75
     還
    0.75
     Correspond
    0.72
    assertEqual
    0.72
    ✯
    0.72
    カイブ
    0.71
    防治
    0.71
     Beneath
    0.70
    POSITIVE LOGITS
     $:
    0.78
    Netherlands
    0.75
    ่า
    0.75
    Fri
    0.75
     snag
    0.74
    แพ
    0.72
    $:
    0.71
     fri
    0.70
    ?:
    0.70
     tablet
    0.70
    Act Density 0.000%

    No Known Activations