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

    Neuronpedia

    INDEX
    Explanations

    news articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     touch
    -0.07
    touch
    -0.07
    Facing
    -0.06
     BATCH
    -0.06
     complicated
    -0.06
    restaurant
    -0.06
     �
    -0.06
     cursos
    -0.06
    Tester
    -0.06
    ग
    -0.06
    POSITIVE LOGITS
     exhibiting
    0.07
     를
    0.06
    قل
    0.06
     uncon
    0.06
     insist
    0.06
    |m
    0.06
     graph
    0.06
     scient
    0.06
     آزمایش
    0.06
     MMA
    0.06
    Act Density 0.054%

    No Known Activations