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

    Neuronpedia

    INDEX
    Explanations

    code loops/iteration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Regions
    -0.07
    -mini
    -0.07
    .DefaultCellStyle
    -0.07
    ******↵↵
    -0.06
    ))
    -0.06
    ways
    -0.06
     lateinit
    -0.06
     ули
    -0.06
    ňuje
    -0.06
    akers
    -0.06
    POSITIVE LOGITS
     контр
    0.06
     encountering
    0.06
     tong
    0.06
     borr
    0.06
     chết
    0.06
    个人
    0.06
     тест
    0.06
     прог
    0.06
     acción
    0.06
     جم
    0.06
    Act Density 0.021%

    No Known Activations