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

    Neuronpedia

    INDEX
    Explanations

    instructions and information

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     perch
    -0.07
     Meng
    -0.07
     Leg
    -0.07
    ł
    -0.06
     Connecticut
    -0.06
     Exiting
    -0.06
    combe
    -0.06
    /fixtures
    -0.06
     Souls
    -0.06
     Hóa
    -0.06
    POSITIVE LOGITS
    strict
    0.07
     bình
    0.07
     UART
    0.06
     треб
    0.06
     Jared
    0.06
    ]={
    0.06
    Jennifer
    0.06
     طبق
    0.06
     Richie
    0.06
     parachute
    0.06
    Act Density 0.021%

    No Known Activations