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

    Neuronpedia

    INDEX
    Explanations

    distribution

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    군
    -0.07
    incorrect
    -0.06
    참
    -0.06
    .cs
    -0.06
     Marine
    -0.06
    县
    -0.06
     актив
    -0.06
    IEEE
    -0.06
     erklä
    -0.06
    .non
    -0.06
    POSITIVE LOGITS
     earners
    0.07
    지고
    0.07
    ními
    0.07
     power
    0.07
    atten
    0.07
    иплом
    0.07
    perienced
    0.06
    官
    0.06
    172
    0.06
    	printk
    0.06
    Act Density 0.000%

    No Known Activations