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

    Neuronpedia

    INDEX
    Explanations

    currency ranges and amounts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     অ্যান
    0.50
    䅐
    0.48
    На
    0.46
     efectuar
    0.46
    Activation
    0.46
    Не
    0.45
    Minutes
    0.45
    AddTime
    0.45
    Tiempo
    0.44
    Harga
    0.44
    POSITIVE LOGITS
     singular
    0.45
     visual
    0.43
    ese
    0.43
    يًا
    0.41
     well
    0.41
     imper
    0.40
     node
    0.40
    -
    0.39
     o
    0.39
     pre
    0.38
    Act Density 0.227%

    No Known Activations