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

    Neuronpedia

    INDEX
    Explanations

    folder and directory

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     as
    1.11
     be
    0.96
     zijn
    0.92
     are
    0.91
     an
    0.88
     klanten
    0.84
     letzte
    0.77
     is
    0.77
     can
    0.77
     größ
    0.76
    POSITIVE LOGITS
    ik
    1.30
    and
    1.03
    ut
    1.02
    od
    0.99
    ana
    0.98
    at
    0.98
     directories
    0.97
    subdirectory
    0.96
     Folder
    0.96
     folders
    0.95
    Act Density 0.048%

    No Known Activations