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

    Neuronpedia

    INDEX
    Explanations

    Encoding artifacts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    اح
    -0.07
     linkage
    -0.07
    側
    -0.07
    )['
    -0.06
    )localObject
    -0.06
    范围
    -0.06
    which
    -0.06
     stakes
    -0.06
     Kap
    -0.06
    MOVED
    -0.06
    POSITIVE LOGITS
     s
    0.08
     
    0.07
    .getOrder
    0.07
     v
    0.07
     K
    0.06
     in
    0.06
    !"
    0.06
     limburg
    0.06
     İşte
    0.06
    router
    0.06
    Act Density 0.072%

    No Known Activations