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

    Neuronpedia

    INDEX
    Explanations

    PHP code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     is
    -0.07
    })(
    -0.07
    ​​
    -0.06
     [][]
    -0.06
     앨
    -0.06
    ox
    -0.06
     <>↵
    -0.06
     campus
    -0.06
     authors
    -0.06
     Raleigh
    -0.06
    POSITIVE LOGITS
    prü
    0.07
    lanır
    0.07
    .Yes
    0.07
    лександ
    0.07
    CommandEvent
    0.06
     eye
    0.06
    _structure
    0.06
    ätt
    0.06
    numbers
    0.06
    Const
    0.06
    Act Density 0.008%

    No Known Activations