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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    グ
    -0.07
    vý
    -0.06
    Periph
    -0.06
    nými
    -0.06
    ến
    -0.06
     ())↵
    -0.06
     потому
    -0.06
     virtue
    -0.06
    _gb
    -0.06
    ọng
    -0.05
    POSITIVE LOGITS
     prophet
    0.07
     converter
    0.07
     Habit
    0.07
    _pic
    0.07
     Beacon
    0.07
    ="#">
    0.06
    conut
    0.06
    PEC
    0.06
     chuckled
    0.06
     inund
    0.06
    Act Density 0.008%

    No Known Activations