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

    Neuronpedia

    INDEX
    Explanations

    programmatic operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    я
    1.02
    ер
    0.96
     Über
    0.94
    så
    0.90
    totime
    0.87
    0.87
    På
    0.84
    Dalam
    0.83
     Former
    0.82
     लोकसभा
    0.82
    POSITIVE LOGITS
    wear
    0.90
    이션
    0.85
     notions
    0.83
     средства
    0.78
     notion
    0.77
    knot
    0.77
     способ
    0.77
     eing
    0.77
     средств
    0.76
    gica
    0.75
    Act Density 0.003%

    No Known Activations