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

    Neuronpedia

    INDEX
    Explanations

    wealth

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     minutos
    -0.08
     하루
    -0.08
    ňují
    -0.07
     Gio
    -0.07
     giorno
    -0.06
     Mädchen
    -0.06
     sınav
    -0.06
     sécurité
    -0.06
    ncoder
    -0.06
    غ
    -0.06
    POSITIVE LOGITS
     wealth
    0.17
     Wealth
    0.16
     wealthy
    0.11
    wealth
    0.10
    alth
    0.09
    ALTH
    0.09
    well
    0.08
    We
    0.07
    Mill
    0.07
     UIL
    0.06
    Act Density 0.004%

    No Known Activations