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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     нату
    -0.07
    Ratio
    -0.06
    Lat
    -0.06
     رفت
    -0.06
     bý
    -0.06
    od
    -0.06
    lund
    -0.06
     professionalism
    -0.06
     десят
    -0.06
     capsule
    -0.06
    POSITIVE LOGITS
     (::
    0.07
     datatable
    0.06
    �
    0.06
    ："
    0.06
    roupe
    0.06
    .Item
    0.06
    /win
    0.06
    ffffffff
    0.06
     FilePath
    0.06
     attendant
    0.06
    Act Density 0.000%

    No Known Activations