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

    Neuronpedia

    INDEX
    Explanations

    we

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wants
    -0.09
     хочет
    -0.09
     غواړي
    -0.09
     wishes
    -0.08
     indicates
    -0.08
     desires
    -0.08
     തന്റെ
    -0.08
     желание
    -0.08
     souhaite
    -0.08
     चाहता
    -0.08
    POSITIVE LOGITS
     છીએ
    0.19
     можем
    0.18
     étions
    0.17
     جميع
    0.17
     all
    0.16
    ’re
    0.16
     avons
    0.16
    ’avons
    0.16
    eping
    0.16
     devons
    0.15
    Act Density 0.059%

    No Known Activations