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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     أمر
    -0.08
     trabal
    -0.07
     Sword
    -0.07
     MW
    -0.06
    หย
    -0.06
     Wein
    -0.06
     Chambers
    -0.06
     куп
    -0.06
     Philip
    -0.06
     kez
    -0.06
    POSITIVE LOGITS
     [%
    0.07
    .Reporting
    0.07
     DataType
    0.07
    .xx
    0.07
     deflate
    0.06
    Charlie
    0.06
    WebHost
    0.06
    Atlanta
    0.06
     recept
    0.06
    uteč
    0.06
    Act Density 0.013%

    No Known Activations