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

    Neuronpedia

    INDEX
    Explanations

    prevalence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    wife
    -0.07
     Whatsapp
    -0.07
     standoff
    -0.07
    Eastern
    -0.07
     Directions
    -0.07
    办事处
    -0.07
    OUNCE
    -0.07
    rocess
    -0.07
    藏着
    -0.07
     advances
    -0.07
    POSITIVE LOGITS
     biểu
    0.09
     prevalence
    0.08
     the
    0.07
    SL
    0.07
    Tbl
    0.07
     statuses
    0.06
    ileo
    0.06
    -V
    0.06
     awakening
    0.06
     pel
    0.06
    Act Density 0.008%

    No Known Activations