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

    Neuronpedia

    INDEX
    Explanations

    Code/Math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     discrepan
    -0.07
    дами
    -0.07
     Control
    -0.06
    ulado
    -0.06
     olanlar
    -0.06
    _HOUR
    -0.06
    _orientation
    -0.06
     Unternehmen
    -0.06
     yaptığ
    -0.06
    ته
    -0.06
    POSITIVE LOGITS
     Invoice
    0.06
     Jays
    0.06
    ucky
    0.06
    ('$
    0.06
    .nome
    0.06
    _variable
    0.06
     Hiring
    0.06
     offerings
    0.06
    Exc
    0.06
    /down
    0.06
    Act Density 0.006%

    No Known Activations