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

    Neuronpedia

    INDEX
    Explanations

    at

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    рения
    -0.07
    iales
    -0.06
    ующих
    -0.06
    ชาต
    -0.06
    ارش
    -0.06
     dazzling
    -0.06
     Fund
    -0.06
     ries
    -0.06
    ládá
    -0.06
    urement
    -0.06
    POSITIVE LOGITS
     slew
    0.07
    .byte
    0.07
    нима
    0.06
     less
    0.06
     finding
    0.06
    ander
    0.06
    merc
    0.06
     catch
    0.06
    (prev
    0.06
     carving
    0.06
    Act Density 0.000%

    No Known Activations