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

    Neuronpedia

    INDEX
    Explanations

    The

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -per
    -0.08
     cà
    -0.08
     गरी
    -0.08
    盈利
    -0.08
     pare
    -0.08
    _PD
    -0.07
     Semiconductor
    -0.07
     touristique
    -0.07
     entrepreneurial
    -0.07
     energética
    -0.07
    POSITIVE LOGITS
    Sword
    0.09
     Sword
    0.09
     sword
    0.09
     quo
    0.08
     арты
    0.08
     Trag
    0.08
     મુદ્દ
    0.08
    approved
    0.07
    ring
    0.07
     ജോ
    0.07
    Act Density 0.011%

    No Known Activations