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

    Neuronpedia

    INDEX
    Explanations

    document

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     payroll
    -0.07
     fz
    -0.07
    Hey
    -0.07
     bef
    -0.06
    azz
    -0.06
    899
    -0.06
     mainly
    -0.06
     capacit
    -0.06
    xyz
    -0.06
     Area
    -0.06
    POSITIVE LOGITS
     documents
    0.11
     document
    0.11
    Document
    0.10
     документів
    0.10
     Document
    0.09
    Documents
    0.09
    documents
    0.09
     Documents
    0.09
     دول
    0.09
     sqlCommand
    0.09
    Act Density 0.045%

    No Known Activations