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

    Neuronpedia

    INDEX
    Explanations

    dates and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     corrupción
    0.49
     autorización
    0.47
     thunderstorm
    0.46
    დას
    0.45
     realises
    0.44
     armament
    0.44
    рель
    0.43
     deputado
    0.42
    ﮑ
    0.42
     oposición
    0.42
    POSITIVE LOGITS
    i
    0.54
    is
    0.51
    options
    0.49
    isering
    0.49
     Options
    0.45
     ٢
    0.44
     options
    0.43
    im
    0.43
     الفور
    0.43
    ти
    0.42
    Act Density 0.013%

    No Known Activations