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

    Neuronpedia

    INDEX
    Explanations

    as

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -helper
    -0.07
     Spiel
    -0.06
     Grand
    -0.06
     ağaç
    -0.06
     Alexis
    -0.06
     Comput
    -0.06
     jewel
    -0.06
     database
    -0.06
     наиболее
    -0.06
    (cursor
    -0.06
    POSITIVE LOGITS
     boss
    0.07
    .lastName
    0.07
    patch
    0.07
    CLOSE
    0.06
     expecting
    0.06
     복
    0.06
    声
    0.06
     Федерации
    0.06
     Clar
    0.06
    ware
    0.06
    Act Density 0.344%

    No Known Activations