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

    Neuronpedia

    INDEX
    Explanations

    Referring to the Reader

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bachelor
    -0.07
    ']);
    -0.07
    259
    -0.06
     Abdul
    -0.06
    _PASS
    -0.06
     debit
    -0.06
    ERVICE
    -0.06
     functionName
    -0.06
    .EXIT
    -0.06
    istrov
    -0.06
    POSITIVE LOGITS
     trick
    0.07
     exploit
    0.07
    Confirmation
    0.07
    iese
    0.06
    .super
    0.06
     gtk
    0.06
    imir
    0.06
     profoundly
    0.06
     sac
    0.06
     $"
    0.06
    Act Density 0.012%

    No Known Activations