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

    Neuronpedia

    INDEX
    Explanations

    the way

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    кла
    0.81
    {}",
    0.80
    Kindly
    0.80
    கி
    0.76
    ER
    0.75
    न्
    0.75
    ′-
    0.75
    க
    0.74
    ಒ
    0.74
    鈥
    0.72
    POSITIVE LOGITS
     way
    1.01
     방식으로
    0.95
     ढंग
    0.90
     तरीके
    0.88
     thức
    0.88
     injective
    0.87
     방식
    0.84
    ática
    0.82
     काढ
    0.81
     ώστε
    0.80
    Act Density 0.095%

    No Known Activations