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

    Neuronpedia

    INDEX
    Explanations

    limits to infinity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Locksmith
    -0.08
    Actor
    -0.08
    处罚
    -0.08
     imput
    -0.07
     ecol
    -0.07
     ẹ
    -0.07
     ಲೋಕ
    -0.07
     تجمع
    -0.07
     uts
    -0.07
     incarceration
    -0.07
    POSITIVE LOGITS
     dominates
    0.13
     dominant
    0.12
    domin
    0.12
     dominate
    0.11
     dominating
    0.11
     dominance
    0.10
    highest
    0.10
    Domin
    0.10
     dominated
    0.10
    argest
    0.09
    Act Density 0.025%

    No Known Activations