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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     கூ
    -0.09
    šno
    -0.08
    [][
    -0.08
    ({},
    -0.08
    (en
    -0.08
    (coeff
    -0.08
    _initialized
    -0.08
     κό
    -0.07
     pū
    -0.07
    _scope
    -0.07
    POSITIVE LOGITS
    曜日
    0.11
     dedicate
    0.10
     सप्ताह
    0.10
     সপ্তাহ
    0.10
     week
    0.09
     semana
    0.09
     Celebrate
    0.09
    星期
    0.09
     sábado
    0.09
     ವಾರ
    0.09
    Act Density 0.008%

    No Known Activations