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

    Neuronpedia

    INDEX
    Explanations

    python code definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hasn
    0.52
    다
    0.46
     storey
    0.45
    Cause
    0.45
    However
    0.45
     occurs
    0.45
    ურთი
    0.45
     hole
    0.45
    是否有
    0.44
    Credit
    0.44
    POSITIVE LOGITS
    ography
    0.42
     Vincenzo
    0.42
     красно
    0.42
     න
    0.42
    ٹس
    0.42
    upyter
    0.41
    モチ
    0.41
     cryptography
    0.41
     freaking
    0.41
    冷静
    0.40
    Act Density 0.001%

    No Known Activations