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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     حج
    -0.07
     unconscious
    -0.06
    spec
    -0.06
    베
    -0.06
    roadcast
    -0.06
    ע
    -0.06
     empty
    -0.06
     irre
    -0.06
    vars
    -0.06
     обращ
    -0.06
    POSITIVE LOGITS
     toolStrip
    0.08
    nero
    0.07
     "))
    0.07
    もしれない
    0.07
     Aug
    0.07
    [])
    0.07
     diaper
    0.07
     Tropical
    0.06
    athering
    0.06
     )))
    0.06
    Act Density 0.088%

    No Known Activations