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

    Neuronpedia

    INDEX
    Explanations

    qualities and characteristics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     twelve
    -0.07
     Article
    -0.07
    任何
    -0.07
    order
    -0.06
    άρ
    -0.06
    ителя
    -0.06
     negro
    -0.06
    次
    -0.06
    λιο
    -0.06
     fifteen
    -0.06
    POSITIVE LOGITS
    _KeyDown
    0.07
     정말
    0.07
     berg
    0.06
     nek
    0.06
    '}>↵
    0.06
     doomed
    0.06
    -have
    0.06
     :)↵
    0.06
     OSC
    0.06
     المش
    0.06
    Act Density 0.191%

    No Known Activations