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

    Neuronpedia

    INDEX
    Explanations

    this

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <Contact
    -0.08
    ted
    -0.07
     outing
    -0.07
    [of
    -0.06
     QDom
    -0.06
    .directory
    -0.06
    -period
    -0.06
     chair
    -0.06
    &e
    -0.06
     kom
    -0.06
    POSITIVE LOGITS
     HMS
    0.07
    inburgh
    0.07
     değerli
    0.06
    alesce
    0.06
     rebuilding
    0.06
     дерев
    0.06
    死
    0.06
    何
    0.06
    Drv
    0.06
    Metric
    0.06
    Act Density 0.001%

    No Known Activations