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

    Neuronpedia

    INDEX
    Explanations

    Citations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     """",↵
    -0.07
    enumerate
    -0.07
     Triangle
    -0.07
    istance
    -0.07
     insistence
    -0.07
     Village
    -0.06
    Series
    -0.06
     Shrine
    -0.06
    -distance
    -0.06
     ноги
    -0.06
    POSITIVE LOGITS
     strategically
    0.06
    locker
    0.06
    "As
    0.06
    aines
    0.06
     Knicks
    0.06
     ignited
    0.06
    titre
    0.05
    _mini
    0.05
     winds
    0.05
     電
    0.05
    Act Density 0.002%

    No Known Activations