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

    Neuronpedia

    INDEX
    Explanations

    install significantly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    eneo
    0.41
     غلام
    0.41
    ologio
    0.40
     quartos
    0.38
    lyde
    0.38
     ಔಷಧ
    0.37
     yana
    0.37
     மான
    0.37
    Medico
    0.36
    ceso
    0.36
    POSITIVE LOGITS
     finca
    0.44
     porch
    0.40
    ઁ
    0.39
     Ủ
    0.38
     virksom
    0.38
     etik
    0.38
    ỏe
    0.38
     winery
    0.38
     coronavirus
    0.37
     interst
    0.37
    Act Density 0.048%

    No Known Activations