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

    Neuronpedia

    INDEX
    Explanations

    drive

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Wash
    -0.07
    週
    -0.06
     wash
    -0.06
    věd
    -0.06
     spolupráci
    -0.06
    acio
    -0.06
     weighs
    -0.06
     mash
    -0.06
    itez
    -0.06
     emoji
    -0.06
    POSITIVE LOGITS
     driven
    0.13
    -driven
    0.11
     drive
    0.09
     driving
    0.08
    Driven
    0.08
    Control
    0.07
     lf
    0.07
     DRIVE
    0.07
    :p
    0.07
    并不
    0.07
    Act Density 0.018%

    No Known Activations