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

    Neuronpedia

    INDEX
    Explanations

    reminders and follow-ups

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Attacks
    -0.07
    .invalidate
    -0.07
    .Execution
    -0.06
     Az
    -0.06
    .r
    -0.06
    212
    -0.06
     Books
    -0.06
     Brief
    -0.06
    irical
    -0.06
    .dex
    -0.06
    POSITIVE LOGITS
     inhab
    0.07
     selfie
    0.07
     thẳng
    0.06
     Xem
    0.06
     ещё
    0.06
     saúde
    0.06
     tuna
    0.06
     NN
    0.06
     HttpContext
    0.06
    ρκ
    0.06
    Act Density 0.186%

    No Known Activations