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

    Neuronpedia

    INDEX
    Explanations

    id

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wash
    -0.08
     conceivable
    -0.08
     analy
    -0.07
     gasp
    -0.07
     zwa
    -0.07
     разработ
    -0.07
     lawful
    -0.07
     кей
    -0.07
    ாத்த
    -0.07
     врем
    -0.07
    POSITIVE LOGITS
     folle
    0.09
    stackoverflow
    0.08
    .Select
    0.08
     يمكنك
    0.08
     tournaments
    0.08
     encontrarás
    0.08
    ريد
    0.08
    .Ignore
    0.08
     ترلاسه
    0.08
     quiser
    0.08
    Act Density 0.006%

    No Known Activations