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

    Neuronpedia

    INDEX
    Explanations

    key

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    IOException
    -0.08
     concessions
    -0.07
    ');↵↵↵↵
    -0.07
    anio
    -0.07
    和平
    -0.07
     specially
    -0.07
    垩
    -0.07
    aneously
    -0.07
     Eigen
    -0.07
     Singapore
    -0.07
    POSITIVE LOGITS
    -power
    0.07
     dumpsters
    0.07
     wines
    0.07
     reloadData
    0.07
     loading
    0.07
     Uploaded
    0.07
     dumpster
    0.07
    前の
    0.07
    Results
    0.07
     demons
    0.07
    Act Density 0.002%

    No Known Activations