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

    Neuronpedia

    INDEX
    Explanations

    marathon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     beliefs
    -0.07
    '$
    -0.07
     Pocket
    -0.07
     Fleming
    -0.06
     Gy
    -0.06
     sentence
    -0.06
     exhibit
    -0.06
     Prince
    -0.06
     eos
    -0.06
     masses
    -0.06
    POSITIVE LOGITS
     Marathon
    0.14
     marathon
    0.13
    athlon
    0.08
    athon
    0.08
    長
    0.07
    aguay
    0.06
     "/";↵
    0.06
    .hour
    0.06
    ner
    0.06
    !!!!!
    0.06
    Act Density 0.002%

    No Known Activations