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

    Neuronpedia

    INDEX
    Explanations

    code formatting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dor
    -0.07
    ASON
    -0.07
     Вал
    -0.06
     рай
    -0.06
     MSC
    -0.06
     Track
    -0.06
    Templates
    -0.06
    Live
    -0.06
     camps
    -0.06
     Frozen
    -0.06
    POSITIVE LOGITS
    До
    0.07
    不断
    0.07
     mũi
    0.07
    der
    0.06
    .Future
    0.06
    麼
    0.06
    .Pages
    0.06
    dropIfExists
    0.06
    黑
    0.06
    hung
    0.06
    Act Density 0.001%

    No Known Activations