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

    Neuronpedia

    INDEX
    Explanations

    invention

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     devs
    -0.07
     ROUT
    -0.06
    justice
    -0.06
    @
    -0.06
     walls
    -0.06
     Coğraf
    -0.06
     Marl
    -0.06
    	Vk
    -0.06
     GANG
    -0.06
    RS
    -0.06
    POSITIVE LOGITS
    يتي
    0.08
    uito
    0.08
    .mvp
    0.07
    νου
    0.07
    swire
    0.07
    よう
    0.06
     needing
    0.06
    -independent
    0.06
    ература
    0.06
    도로
    0.06
    Act Density 0.011%

    No Known Activations