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

    Neuronpedia

    INDEX
    Explanations

    Professions and law

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	x
    -0.07
    MS
    -0.06
     Templ
    -0.06
     creditor
    -0.06
    ีต
    -0.06
    CHOOL
    -0.06
     그가
    -0.06
     edt
    -0.06
    upil
    -0.06
     сп
    -0.06
    POSITIVE LOGITS
     ornament
    0.07
    .authorization
    0.07
    erializer
    0.07
    yar
    0.06
    NotSupportedException
    0.06
     профессиональ
    0.06
    /*↵
    0.06
     horizontally
    0.06
     Chương
    0.06
     waivers
    0.06
    Act Density 0.047%

    No Known Activations