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

    Neuronpedia

    INDEX
    Explanations

    settings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lett
    -0.07
     nargs
    -0.06
    _mar
    -0.06
     area
    -0.06
    actories
    -0.06
     наличии
    -0.06
    Catalog
    -0.06
    obia
    -0.06
    ціон
    -0.06
    едак
    -0.06
    POSITIVE LOGITS
    Hillary
    0.06
     Advocate
    0.06
     Steve
    0.06
    ">'+↵
    0.06
     Plan
    0.06
    Disney
    0.06
    Visual
    0.06
    --------
    0.06
    Steve
    0.06
     。↵
    0.06
    Act Density 0.011%

    No Known Activations