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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    club
    -0.07
    Mixin
    -0.07
     Late
    -0.06
     suppressed
    -0.06
     почему
    -0.06
    .GetObject
    -0.06
    uture
    -0.06
     Stops
    -0.06
     communism
    -0.06
     sucks
    -0.06
    POSITIVE LOGITS
    ือ
    0.08
     Chairman
    0.06
     بد
    0.06
     فض
    0.06
    �
    0.06
    Cloud
    0.06
    {
    0.06
    ubble
    0.06
     BigInt
    0.06
     caching
    0.06
    Act Density 0.047%

    No Known Activations