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

    Neuronpedia

    INDEX
    Explanations

    finance and data analysis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    chosen
    0.55
     millón
    0.50
    Ḵ
    0.49
    caso
    0.48
     pér
    0.47
     Mendez
    0.45
    ství
    0.45
    ડિયા
    0.44
     lesión
    0.44
     tých
    0.44
    POSITIVE LOGITS
    灼
    0.41
    Timing
    0.41
    时
    0.40
    ayaran
    0.40
    的时
    0.40
     Timing
    0.40
    өг
    0.39
     ذریع
    0.39
    propylene
    0.39
    .
    0.39
    Act Density 0.002%

    No Known Activations