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

    Neuronpedia

    INDEX
    Explanations

    symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     preorder
    -0.07
     daar
    -0.06
     tomto
    -0.06
     ---------
    -0.06
     ++↵
    -0.06
     reservation
    -0.06
     iphone
    -0.06
    -volume
    -0.06
     -->↵
    -0.06
     earlier
    -0.06
    POSITIVE LOGITS
     thwart
    0.07
    стро
    0.06
    ện
    0.06
     EXTI
    0.06
     unarmed
    0.06
    ậy
    0.06
    けた
    0.06
     Creates
    0.06
     tendr
    0.06
    interactive
    0.06
    Act Density 0.075%

    No Known Activations