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

    Neuronpedia

    INDEX
    Explanations

    punctuation or "or"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     they'd
    -0.10
    mnopqrstuvwxyz
    -0.09
     they'll
    -0.09
     받은
    -0.09
     We'll
    -0.08
     that'll
    -0.08
     recieved
    -0.08
     alred
    -0.08
     recieve
    -0.08
     وسوف
    -0.08
    POSITIVE LOGITS
     cybersecurity
    0.09
    某
    0.09
    Finance
    0.08
    比如
    0.08
    Financial
    0.08
     automotive
    0.08
    金融
    0.07
     finance
    0.07
    Audio
    0.07
    物流
    0.07
    Act Density 0.151%

    No Known Activations