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

    Neuronpedia

    INDEX
    Explanations

    RT

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ->_
    -0.08
    Evaluator
    -0.07
    Polynomial
    -0.07
     Perspective
    -0.07
     devoir
    -0.07
    iou
    -0.07
    Epoch
    -0.07
     Polynomial
    -0.07
    owaniu
    -0.07
     याद
    -0.07
    POSITIVE LOGITS
     obras
    0.08
     soluções
    0.08
    方案
    0.08
     sanitaires
    0.08
    _projects
    0.08
     waterfront
    0.08
     решения
    0.08
     corridor
    0.08
     năng
    0.08
     stroller
    0.08
    Act Density 0.002%

    No Known Activations