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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rut
    -0.07
     privilege
    -0.07
    ucs
    -0.07
    uka
    -0.06
    諾
    -0.06
    %)↵
    -0.06
    ۲۳
    -0.06
     wait
    -0.06
    -med
    -0.06
     mention
    -0.06
    POSITIVE LOGITS
     удар
    0.07
     setState
    0.06
    _magic
    0.06
    tableName
    0.06
     stanice
    0.06
     الل
    0.06
    [number
    0.06
     운영자
    0.06
    gambar
    0.06
     مرة
    0.06
    Act Density 0.109%

    No Known Activations