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

    Neuronpedia

    INDEX
    Explanations

    academic publications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sedation
    -0.10
    colors
    -0.08
     smiling
    -0.08
     segmentation
    -0.08
     backgrounds
    -0.08
     lasers
    -0.08
    health
    -0.08
     health
    -0.08
     cosmetics
    -0.07
     saúde
    -0.07
    POSITIVE LOGITS
     गृह
    0.09
     literary
    0.08
     tortor
    0.08
    季度
    0.08
     osp
    0.08
    偶
    0.08
    ырга
    0.08
     débat
    0.08
     неожидан
    0.08
    文学
    0.08
    Act Density 0.006%

    No Known Activations