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

    Neuronpedia

    INDEX
    Explanations

    equivalence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    zone
    -0.08
     সহ
    -0.08
     که
    -0.08
     følger
    -0.07
     مح
    -0.07
     அற
    -0.07
     পরীক্ষা
    -0.07
    ền
    -0.07
     ব্যক্তি
    -0.07
     বজ
    -0.07
    POSITIVE LOGITS
     penchant
    0.10
     скорость
    0.09
     reputation
    0.09
     procès
    0.08
     Situs
    0.08
     chances
    0.08
     скорости
    0.08
     происх
    0.08
     qualities
    0.08
     lloc
    0.08
    Act Density 0.073%

    No Known Activations