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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -0.08
    -0.08
    <strong
    -0.08
     utilization
    -0.08
     SIS
    -0.07
     FIR
    -0.07
     Fortunately
    -0.07
    -
    -0.07
     constant
    -0.07
    [X
    -0.07
    POSITIVE LOGITS
     vestido
    0.10
     vestidos
    0.10
     regal
    0.09
    Vintage
    0.09
     protagon
    0.09
     protagonista
    0.09
     dresses
    0.09
    裸體
    0.09
     whakaaro
    0.09
    ાવવા
    0.09
    Act Density 0.002%
    No Known Activations