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

    Neuronpedia

    INDEX
    Explanations

    voting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     neighbors
    -0.07
    098
    -0.07
     nueva
    -0.06
     Whe
    -0.06
     situations
    -0.06
    跑
    -0.06
     purse
    -0.06
     sushi
    -0.06
    Ber
    -0.06
     док
    -0.06
    POSITIVE LOGITS
    	Main
    0.07
     Halifax
    0.07
    /routes
    0.06
    configs
    0.06
    jobs
    0.06
    <Scalar
    0.06
    .constraint
    0.06
    istani
    0.06
     shrink
    0.06
    (cos
    0.06
    Act Density 0.011%

    No Known Activations