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
    [cnt
    -0.07
    _FL
    -0.07
     мик
    -0.06
     císa
    -0.06
    ональ
    -0.06
     bus
    -0.06
    inqu
    -0.06
     spokesman
    -0.06
     criticized
    -0.06
     правиль
    -0.06
    POSITIVE LOGITS
     Hóa
    0.06
    \:
    0.06
     Received
    0.06
     jin
    0.06
    geist
    0.06
     пер
    0.06
    .Serial
    0.06
     twins
    0.05
    传奇
    0.05
    loan
    0.05
    Act Density 0.538%

    No Known Activations