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

    Neuronpedia

    INDEX
    Explanations

    negation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     containers
    -0.07
     مشک
    -0.06
    .savetxt
    -0.06
    -pic
    -0.06
    然
    -0.06
     �
    -0.06
     assez
    -0.06
     فرض
    -0.06
     wear
    -0.06
    Status
    -0.06
    POSITIVE LOGITS
    ")->
    0.07
    .dep
    0.06
     улуч
    0.06
    _locations
    0.06
     UFO
    0.06
    ViewController
    0.06
    ,:),
    0.06
    ována
    0.06
    [vertex
    0.06
    ymi
    0.06
    Act Density 0.013%

    No Known Activations