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

    Neuronpedia

    INDEX
    Explanations

    Intersections

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    amilies
    -0.07
    zung
    -0.07
     Friends
    -0.07
     fooled
    -0.07
     WALL
    -0.07
     Brilliant
    -0.07
    わず
    -0.06
     Prest
    -0.06
     فاصله
    -0.06
     puppy
    -0.06
    POSITIVE LOGITS
    ideal
    0.06
     Govern
    0.06
    _append
    0.06
     отрим
    0.06
     faucet
    0.06
     енерг
    0.06
    urma
    0.05
     أ
    0.05
     limbs
    0.05
     آینده
    0.05
    Act Density 0.221%

    No Known Activations