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

    Neuronpedia

    INDEX
    Explanations

    explaining why or how natives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Western
    0.43
    Reviewed
    0.41
    ків
    0.41
    Professional
    0.41
    solved
    0.41
    すべての
    0.41
    hotels
    0.40
    most
    0.39
    世界の
    0.39
    western
    0.39
    POSITIVE LOGITS
     picnics
    0.45
     🌱
    0.44
     flyers
    0.44
     selfies
    0.44
    ይል
    0.41
     Natives
    0.40
     millennials
    0.40
     Millennials
    0.40
     hashtags
    0.39
     headlights
    0.39
    Act Density 0.009%

    No Known Activations