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

    Neuronpedia

    INDEX
    Explanations

    only, because "only" is the most frequent

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    laden
    -0.06
    gal
    -0.06
     BF
    -0.06
    verification
    -0.06
     determinant
    -0.06
    setting
    -0.06
     officially
    -0.06
    ideshow
    -0.06
    ulla
    -0.06
    }->{
    -0.06
    POSITIVE LOGITS
    |h
    0.06
    (directory
    0.06
     Lisbon
    0.06
     Zy
    0.06
    яж
    0.06
     Daisy
    0.06
     Kaw
    0.06
    (withDuration
    0.06
    再
    0.06
    -parse
    0.06
    Act Density 0.003%

    No Known Activations