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

    Neuronpedia

    INDEX
    Explanations

    observ

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     diplomatic
    -0.08
     profits
    -0.08
     taller
    -0.08
     angi
    -0.08
    Рост
    -0.08
     growth
    -0.08
     inser
    -0.08
     downtown
    -0.08
    -cols
    -0.07
     listings
    -0.07
    POSITIVE LOGITS
     rituals
    0.11
     पालन
    0.10
     соблюдать
    0.10
     compuls
    0.09
     नियम
    0.09
     obedience
    0.09
     práctica
    0.08
     Jenner
    0.08
     ritual
    0.08
    规范
    0.08
    Act Density 0.016%

    No Known Activations