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

    Neuronpedia

    INDEX
    Explanations

    Filtering/restricting outputs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    füh
    -0.06
    drm
    -0.06
    .geom
    -0.06
     kommer
    -0.06
    औ
    -0.06
     Zoo
    -0.06
     urinary
    -0.06
    :'↵
    -0.06
     名無し
    -0.06
    .Line
    -0.06
    POSITIVE LOGITS
     confronted
    0.07
     Kosovo
    0.07
     terrorists
    0.06
    547
    0.06
    Australian
    0.06
     directions
    0.06
    alist
    0.06
     Michigan
    0.06
     terminated
    0.06
     Florida
    0.06
    Act Density 0.001%

    No Known Activations