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

    Neuronpedia

    INDEX
    Explanations

    multiple languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    stuff
    -0.09
    Stuff
    -0.09
     Renting
    -0.09
     জ
    -0.08
    170
    -0.08
     Forgot
    -0.08
     deform
    -0.08
    -ish
    -0.08
     ഒഴ
    -0.08
     Swipe
    -0.07
    POSITIVE LOGITS
     غذایی
    0.09
     mundial
    0.09
    ทาง
    0.08
     internet
    0.08
     Ventura
    0.08
     Chin
    0.07
     potr
    0.07
     kho
    0.07
     интернет
    0.07
     المالية
    0.07
    Act Density 0.074%

    No Known Activations