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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     contractors
    -0.07
     external
    -0.07
     obviously
    -0.06
    (fn
    -0.06
     crore
    -0.06
     btc
    -0.06
    bero
    -0.06
     testimon
    -0.06
     sandwiches
    -0.06
     проблема
    -0.06
    POSITIVE LOGITS
    London
    0.07
    izi
    0.07
    pections
    0.07
    VENTORY
    0.06
    HR
    0.06
    )viewDidLoad
    0.06
    zę
    0.06
     ماده
    0.06
     Html
    0.06
     tiener
    0.06
    Act Density 0.035%

    No Known Activations