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

    Neuronpedia

    INDEX
    Explanations

    kol

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    line
    -0.06
     checks
    -0.06
     Filters
    -0.06
     çoğu
    -0.06
     evenly
    -0.06
    road
    -0.06
     intrigued
    -0.06
    Tracks
    -0.06
     sea
    -0.06
     Protected
    -0.06
    POSITIVE LOGITS
     школи
    0.07
     Респ
    0.07
     coh
    0.07
    relay
    0.06
    �
    0.06
     plais
    0.06
     сов
    0.06
     المغرب
    0.06
    .events
    0.06
    кол
    0.06
    Act Density 0.004%

    No Known Activations