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

    Neuronpedia

    INDEX
    Explanations

    Code and data files

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     footh
    -0.06
    (userName
    -0.06
    ёр
    -0.06
     vývoj
    -0.06
    .ContainsKey
    -0.06
    .ak
    -0.06
     
    -0.06
    сия
    -0.06
     فه
    -0.06
    ализи
    -0.06
    POSITIVE LOGITS
     \|
    0.07
     shops
    0.07
     эф
    0.06
     depicted
    0.06
     Olympia
    0.06
     blanket
    0.06
    Callbacks
    0.06
     تفاوت
    0.06
    竞
    0.06
     space
    0.06
    Act Density 0.226%

    No Known Activations