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

    Neuronpedia

    INDEX
    Explanations

    express

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     express
    -1.72
    express
    -1.48
    Express
    -1.39
     Express
    -1.38
     expression
    -1.34
     EXPRESS
    -1.30
    expression
    -1.20
     address
    -1.19
     expressing
    -1.12
     expressed
    -1.11
    POSITIVE LOGITS
     виправивши
    1.08
    OGND
    0.74
     مشين
    0.74
     ProtoMessage
    0.73
    expandindo
    0.69
     doInBackground
    0.68
     lenker
    0.67
     utafitiHapana
    0.66
    manship
    0.66
     disambiguazione
    0.66
    Act Density 1.645%

    No Known Activations