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

    Neuronpedia

    INDEX
    Explanations

    speaker drivers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Islington
    0.40
     destin
    0.35
    separated
    0.35
    attha
    0.34
    漬
    0.33
     arte
    0.33
     scaled
    0.33
    olok
    0.33
    礎
    0.32
    齙
    0.32
    POSITIVE LOGITS
     drivers
    0.92
     driver
    0.87
    Driver
    0.85
    Drivers
    0.84
     cone
    0.82
     Driver
    0.80
     Drivers
    0.79
     ड्राइवर
    0.77
    driver
    0.76
     драй
    0.75
    Act Density 0.015%

    No Known Activations