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

    Neuronpedia

    INDEX
    Explanations

    Comparing plants

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     왕
    -0.07
     Ve
    -0.06
     escorts
    -0.06
     nhân
    -0.06
     당
    -0.06
     дв
    -0.06
    declaration
    -0.06
     теч
    -0.06
     Elementary
    -0.06
     ess
    -0.06
    POSITIVE LOGITS
    published
    0.07
     silenced
    0.07
     researched
    0.07
    AndView
    0.07
    (JSON
    0.06
     Positioned
    0.06
    Filed
    0.06
    @Override
    0.06
    _epoch
    0.06
     naï
    0.06
    Act Density 0.011%

    No Known Activations