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

    Neuronpedia

    INDEX
    Explanations

    address

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     MOT
    -0.06
     Gordon
    -0.06
    겠
    -0.06
    mamak
    -0.06
    imeter
    -0.06
     Meadow
    -0.06
    PDO
    -0.06
    (LOG
    -0.06
     explosives
    -0.06
    واز
    -0.06
    POSITIVE LOGITS
    Pay
    0.06
     عدد
    0.06
     thoughts
    0.06
    Writable
    0.06
    ск
    0.06
     deciding
    0.06
     만
    0.06
    ائع
    0.06
    vy
    0.06
    την
    0.06
    Act Density 0.013%

    No Known Activations