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

    Neuronpedia

    INDEX
    Explanations

    average, wonderful, masterpiece

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    кса
    0.50
     рынке
    0.47
     coupes
    0.45
    ларда
    0.44
    ಮಾರ
    0.43
     tempest
    0.43
     рынок
    0.41
     нажмите
    0.41
    правля
    0.41
    றிவு
    0.41
    POSITIVE LOGITS
    US
    0.53
    example
    0.51
    Product
    0.45
    Gender
    0.43
    Their
    0.43
    program
    0.42
    Average
    0.42
    ER
    0.42
    Effect
    0.42
    B
    0.42
    Act Density 0.004%

    No Known Activations